AACFlow против OpenAI AgentKit
AACFlow — ИИ-рабочее пространство, где команды создают, развёртывают и сопровождают ИИ-агентов визуально, в диалоге или кодом. Вот как AACFlow соотносится с OpenAI AgentKit по архитектуре платформы, возможностям ИИ, интеграциям, ценам, безопасности и поддержке. Каждый факт ниже подтверждён источником и датой, последняя проверка: .
AACFlow — ИИ-рабочее пространство для создания, развёртывания и сопровождения ИИ-агентов. На этой странице AACFlow сравнивается с OpenAI AgentKit по архитектуре платформы, возможностям ИИ, интеграциям, ценам, безопасности и соответствию требованиям, наблюдаемости и поддержке; используются факты с источниками и датами для тех, кто выбирает между двумя платформами.
Что такое AACFlow?
AACFlow is the AI workspace where teams build, deploy, and manage AI agents, connecting 1,000+ integrations and every major LLM to automate real work visually, conversationally, or with code.
Что такое OpenAI AgentKit?
OpenAI AgentKit bundled a visual Agent Builder, ChatKit embeddable chat UI, Connector Registry, Guardrails, and Evals for building agentic workflows on OpenAI's models. But OpenAI is winding down Agent Builder and Evals, with full shutdown November 30, 2026, in favor of the code-first Agents SDK or ChatGPT Workspace Agents.
AACFlow и OpenAI AgentKit: сравнение по возможностям
В разделах ниже AACFlow и OpenAI AgentKit сравниваются по платформе и развёртыванию, ценам, безопасности и соответствию требованиям, возможностям ИИ, интеграциям, наблюдаемости и поддержке.
Платформа и развёртывание
AACFlow offers a visual builder and promotion across environments. OpenAI Agent Builder is a hosted visual canvas that OpenAI is retiring, leaving the code-first Agents SDK as its successor.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Тип конструктора
AACFlow
Visual canvas, chat, or code (источник: AACFlow Docs: Introduction (visual, natural-language, and API/SDK building), откроется в новой вкладке)Visual drag-and-drop canvas, natural-language (Chat), or code (API/SDK)
OpenAI AgentKit
Visual canvas, deprecated in favor of code-first SDK (источник: OpenAI Community: Deprecation notice - Agent Builder, откроется в новой вкладке)Visual canvas (Agent Builder) for drag-and-drop multi-agent workflow construction, paired with a code-first alternative (Agents SDK, Python/TypeScript). Agent Builder was a visual, node-based canvas for creating and versioning multi-agent workflows with typed inputs/outputs and live-data preview. It is being deprecated in favor of the code-first Agents SDK, making the long-term builder paradigm code-based rather than visual.
Порог входа
AACFlow
Low, plus natural-language Chat for non-technical users (источник: AACFlow Docs: Introduction (visual, natural-language, and API/SDK building), откроется в новой вкладке)Low for visual building; natural-language Chat surface (with a workflow-scoped Copilot) for non-technical builders. Chat lets users describe a workflow in plain language and have AACFlow scaffold or edit it; the visual canvas requires no code to connect blocks.
OpenAI AgentKit
Not publicly documentedUnknown. Agent Builder targeted low-code use and the Agents SDK targets Python/TypeScript developers, but no source quantifies the learning curve for either.
Варианты развёртывания
AACFlow
Managed cloud, no single-tenant VPC option (источник: AACFlow Pricing Page, откроется в новой вкладке)Cloud-hosted (managed, multi-tenant SaaS) operated by AACFlow. No documented managed single-tenant/VPC hosting tier. AACFlow is sold as a managed cloud service; there is no dedicated-instance/VPC offering.
OpenAI AgentKit
OpenAI-hosted only; Agents SDK deploys anywhere (источник: Cloudflare Blog: Building agents with OpenAI and Cloudflare Agents SDK, откроется в новой вкладке)OpenAI-hosted cloud only for Agent Builder/Evals (being shut down); Agents SDK code can be deployed anywhere that runs Python/TypeScript (e.g., AWS Lambda, Cloudflare Workers, FastAPI servers). There is no official Docker/Kubernetes distribution of AgentKit itself; deployment flexibility comes from the open-source Agents SDK being ordinary application code, as demonstrated by third-party deployment guides running it on Cloudflare Workers/Durable Objects and on AWS Lambda behind a FastAPI wrapper.
Шаблоны
AACFlow
(источник: AACFlow codebase: templates gallery and APIs removed, откроется в новой вкладке)No: the pre-built workflow template gallery (landing and in-workspace) was removed platform-wide. AACFlow now surfaces per-integration starter prompts instead of a template library.
OpenAI AgentKit
(источник: OpenAI Cookbook: AgentKit walkthrough, откроется в новой вкладке)Yes: Agent Builder provided templates for common workflow patterns, and a ChatKit starter template. Agent Builder let users start from templates and drag and drop nodes for each step in a workflow. This feature is tied to Agent Builder, which is being deprecated.
Продвижение между средами
AACFlow
(источник: AACFlow Docs: Workspace Forks, откроется в новой вкладке)Yes: fork a whole workspace into a dev/qa/prod-style child, diff it, and promote or roll back changes in either direction. Credential and env-var remapping is required before every promote, so secrets are never silently copied across environments. Gated to the Enterprise plan.
OpenAI AgentKit
(источник: Agent Builder guide (deprecation notice), откроется в новой вкладке)No dev/qa/prod-style environment promotion for full projects. Only single-workflow versioning and code export. Agent Builder workflows export as code (Agents SDK, Python or TypeScript) or JSON templates, and templates can sync with a Git repo for reuse, but there's no built-in feature to clone a whole project and promote it between dev/qa/prod environments. Promoting environments means exporting to code and managing them yourself, which lines up with third-party reviews noting Agent Builder lacks production-grade deployment pipelines.
Контроль версий
AACFlow
Deployment rollback plus Copilot edit diff/revert (источник: AACFlow codebase: WorkflowDiffEngine, откроется в новой вкладке)Deployed-version history with rollback for every workflow; server-persisted checkpoint/revert and visual diff (accept/reject) specifically for Copilot AI edits. Manual drag-and-drop undo/redo is client-side/localStorage only (capped at 100 ops, 5 stacks), not server-synced across devices. Deployment history does not include an arbitrary version-to-version diff tool, and knowledge base documents have no version history.
OpenAI AgentKit
Version snapshots, no rollback or diff view (источник: Agent Builder guide, откроется в новой вкладке)Publish creates a major version snapshot; API can target older versions; autosave + manual checkpoints, but no documented rollback UI, diff/compare view, or branching. Publishing a workflow in Agent Builder creates a new major version acting as a snapshot, and API calls can target an older version. The workspace autosaves continuously and supports manual version checkpoints, but there is no rollback button, visual diff/compare-versions view, or branching. Third-party reviews note Agent Builder still lacks production-grade features like rollback, observability, and deployment pipelines.
Совместная работа в реальном времени
AACFlow
(источник: AACFlow codebase: realtime presence handler (cursor/selection broadcast), откроется в новой вкладке)Yes: live multiplayer editing of the same workflow canvas, with real-time cursors, selection broadcasting, and synced concurrent edits over a dedicated realtime backend
OpenAI AgentKit
(источник: Agent Builder | OpenAI API, откроется в новой вкладке)No: OpenAI does not document live, multi-user editing of the same Agent Builder canvas with shared cursors or selections. Teams instead collaborate asynchronously, by importing/exporting workflow JSON, syncing with a Git repo, and publishing versioned snapshots.. Some third-party blog posts describe Agent Builder as supporting 'collaborative editing,' but this isn't confirmed in official OpenAI docs and likely refers to the async JSON/Git sharing model.
Встроенное файловое хранилище
AACFlow
(источник: AACFlow codebase: file share modal (password/email/SSO modes), откроется в новой вкладке)Yes: a native Files area with folder hierarchy, link-based sharing (public, password, email OTP, or SSO auth), and a workspace-level Recently Deleted view covering workflows, tables, knowledge bases, files, and folders. Admins can restrict which share-auth modes (public/password/email/SSO) a permission group is allowed to use.
OpenAI AgentKit
(источник: Tools: Connectors and MCP servers | OpenAI Platform, откроется в новой вкладке)No: Agent Builder/AgentKit has no file storage system of its own (no folders, link sharing, or deleted-item recovery). Files are instead handled through the Connector Registry, which points to external storage providers (Dropbox, Google Drive, SharePoint, Microsoft Teams), or through per-call uploads to file search/code interpreter.
Встроенные таблицы данных
AACFlow
(источник: AACFlow Docs: Tables, откроется в новой вкладке)Yes: a native spreadsheet-like Tables feature (typed columns, not an external DB connector) with full keyboard support (arrow keys, Tab, copy-paste bulk load, Cmd/Ctrl+Z undo) and atomic per-row writes from multiple workflows at once. No public fixed row-limit figure is documented (guidance says paginate reads past ~100k rows); a workflow can also be wired to run per row via a "workflow column."
OpenAI AgentKit
(источник: Node reference | OpenAI API, откроется в новой вкладке)No: AgentKit has no equivalent to a native Tables feature. Agent Builder's 'State' and 'Data' nodes are in-workflow variables and data-reshaping steps scoped to a single run, not a persistent, spreadsheet-like data store with typed columns, rows, or keyboard navigation (arrow keys, copy-paste across cells) that other workflows or runs can read and write.. Set State defines counters, flags, or contextual values referenced by later nodes in the same run; Data nodes reshape outputs (e.g., object to array) or define global variables for that run. Neither persists rows across separate workflow executions or exposes a spreadsheet UI. Structured, persistent storage that outlives a single run has to come from an external system reached through a connector or MCP server (e.g., a Google Sheets or database connector), not a database or table feature built into AgentKit itself.
Редактор документов с форматированием
AACFlow
(источник: AACFlow codebase: rich markdown editor, откроется в новой вкладке)Yes: markdown files opened in the Files viewer render in an inline WYSIWYG-style rich markdown editor, with inline @-mention links to other AACFlow resources
OpenAI AgentKit
(источник: ChatKit widgets | OpenAI API, откроется в новой вкладке)No: Agent Builder/AgentKit has no native, inline rich-text (WYSIWYG) document editor. Text is written in plain node fields and prompts, and ChatKit widgets render structured cards, lists, and components rather than acting as a document editor.
Подворкфлоу (композиция)
AACFlow
(источник: AACFlow Docs: Workflow block, откроется в новой вкладке)Yes: a Workflow block calls another saved workflow as a step, waits for it to finish, runs its latest deployed version, and maps parent variables into the child's input form. Self-references are blocked to prevent infinite recursion.
OpenAI AgentKit
(источник: Node reference | OpenAI API, откроется в новой вкладке)No: Agent Builder's node reference (Start, Agent, Note, File search, Guardrails, MCP, If/else, While, Human approval, Transform, Set state) has no node that calls a separate saved workflow as a nested step and waits for it to finish. Composition across agents happens via handoffs between Agent nodes within the same workflow canvas, not by invoking another independently saved workflow as a reusable child step.. A workflow can call other agents through handoffs (execution transfers to another Agent node, carrying conversation state), but that is agent-to-agent handoff inside one workflow graph, not a call-another-workflow-and-return block. The only way to reuse a workflow elsewhere is to export it as Agents SDK code and call that code from other code, a code-level reuse pattern rather than a visual sub-workflow step.
Собственные блоки (повторное использование в организации)
AACFlow
(источник: AACFlow codebase: custom-blocks publish API (admin gate), откроется в новой вкладке)Yes: a user with admin access on a workflow's workspace can publish its deployed version as a named, iconed custom block that appears in the block toolbar for the whole organization. Inputs are read live from the source workflow's Start block; the publisher picks which outputs to expose. The block always runs the source workflow's latest deployed version, and its internal steps and intermediate values are never exposed to consumers. Enterprise-gated. Distinct from the Workflow (sub-workflow) block, which composes a workflow the same author controls, and from custom code/tool blocks, which run inline code rather than a full deployed workflow.
OpenAI AgentKit
(источник: Node reference | OpenAI API, откроется в новой вкладке)No: Agent Builder has no feature to publish a workflow as a named, encapsulated block that other org members can drop into their own separate workflows.. Its node palette has no 'workflow as a block' node, and the documented reuse paths (templates, ChatKit, SDK code export) give teammates a copy or an endpoint, never a live encapsulated block that stays in sync with the source workflow's latest published version.
Тарифы
AACFlow combines a per-user subscription with usage credits and bring-your-own-key exemptions, while OpenAI charges for model tokens and tools without a dedicated AgentKit plan. Estimate workflow volume, token consumption, and paid tool calls when comparing total cost.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Модель ценообразования
AACFlow
Credit-based billing, BYOK exempt from caps (источник: AACFlow Pricing, откроется в новой вкладке)Credit-based usage billing (Stripe), with bring-your-own-key exemption from metered caps
OpenAI AgentKit
Usage-based tokens plus tool fees (источник: OpenAI API Pricing, откроется в новой вкладке)Usage-based (per-token model pricing plus per-call/per-session tool pricing). No flat AgentKit subscription. Agent Builder was free to design in. Costs are incurred only when workflows run, through standard OpenAI API token pricing (e.g., gpt-5.5: $5.00/M input, $30.00/M output tokens) plus tool-specific charges: Code Interpreter runs $0.03-$1.92 per session by memory tier (billed per minute, five-minute minimum), and File Search costs $0.10/GB-day for storage (1 GB free) plus $2.50 per 1,000 tool calls. Agent Builder itself is being deprecated, with full shutdown November 30, 2026, so this pricing model applies only until then.
Начальный платный тариф
AACFlow
Pro plan at $25/user/month (источник: AACFlow Pricing, откроется в новой вкладке)Pro: $25 per user/month
OpenAI AgentKit
(источник: OpenAI API Pricing, откроется в новой вкладке)No dedicated AgentKit plan; costs are pay-as-you-go API usage starting from $0 committed spend. There is no AgentKit-specific entry paid tier. Billing is metered API usage (tokens plus tool calls) as described under pricing model.
Бесплатный уровень
AACFlow
(источник: AACFlow Pricing, откроется в новой вкладке)No free tier: usage is paid for with prepaid wallet credits or a paid plan
OpenAI AgentKit
(источник: OpenAI API Pricing, откроется в новой вкладке)Yes, partially: Agent Builder was free to design in, and ChatKit/File Search each include an initial 1 GB of free storage before per-GB-day charges apply. Agent Builder let you design and iterate at zero cost until you ran a workflow. ChatKit includes 1 GB of free file/image storage per account per month before $0.10/GB-day applies, and File Search includes a one-time free GB of storage before the same rate applies, a standing allowance rather than a recurring daily reset.
Собственный ключ (BYOK)
AACFlow
(источник: AACFlow Docs: Bring Your Own Key (BYOK), откроется в новой вкладке)Yes: bring-your-own-key support exempts usage from metered credit caps, and multiple keys stored for the same provider are automatically round-robin rotated, with automatic fallback past any key that fails to decrypt
OpenAI AgentKit
No; OpenAI models only (источник: OpenAI API Pricing, откроется в новой вкладке)Not applicable / no. AgentKit runs exclusively on OpenAI's own billed models; there is no BYOK mechanism to swap in a different LLM provider's API key. Since all model calls route through OpenAI's own metered API, there's no bring-your-own-key concept for third-party LLM providers within Agent Builder or the Agents SDK the way a multi-LLM platform would offer it.
Безопасность и соответствие требованиям
OpenAI publishes a broader certification portfolio, while AACFlow provides more direct infrastructure control through self-hosting and configurable credential, retention, session, and audit policies.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
SOC 2
AACFlow
(источник: AACFlow Landing Page, откроется в новой вкладке)No third-party SOC 2 report is claimed
OpenAI AgentKit
(источник: OpenAI Trust Portal (SafeBase), откроется в новой вкладке)Yes: SOC 2 Type 2, plus ISO 27001, 27017, 27018, and 27701 certifications. OpenAI's most recent SOC 2 report covers January 1, 2025 through June 30, 2025 for Security, Availability, Confidentiality, and Privacy Trust Services Criteria across the API Platform, ChatGPT Enterprise, ChatGPT Edu, and ChatGPT Team.
Резидентность данных
AACFlow
Cloud region toggle is global, not per-customer (источник: AACFlow codebase: async job region resolution, откроется в новой вкладке)On AACFlow Cloud, async job execution has an internal US/EU region toggle, but it is deployment-wide, not a customer-selectable per-workspace residency option
OpenAI AgentKit
(источник: Expanding data residency access to business customers worldwide, откроется в новой вкладке)Yes: data residency at rest available in US, Europe, UK, Japan, Canada, South Korea, Singapore, Australia, India, and UAE for eligible enterprise customers. Eligible ChatGPT Enterprise, ChatGPT Edu, ChatGPT for Healthcare, and API platform customers can store content at rest in these regions; eligible customers can also opt into in-region GPU inference in the U.S. or Europe.
Ролевой контроль доступа
AACFlow
(источник: AACFlow Docs: Roles and Permissions, откроется в новой вкладке)Yes: admin/write/read workspace permissions, org-level admin/member roles, plus Enterprise-tier permission groups that allow/deny-list specific models, tools, and integrations per group on top of those base roles. See modelAndToolGovernance and credentialGovernance for the finer-grained permission-groups layer.
OpenAI AgentKit
(источник: RBAC | OpenAI Help Center, откроется в новой вкладке)Yes, at the workspace level. Workspace Owners create custom roles and use per-role "Connected data" controls to allow or restrict which apps/connectors (and their actions) each role can use, with all apps disabled by default. A separate Global Admin Console (beta) adds a distinct Global admin role for centralizing access management across workspaces. Granular access scoped to individual Agent Builder workflows is not documented.. ChatGPT Enterprise/Edu/Business workspaces let Workspace Owners create custom roles and, under each role's Connected data section, turn on "Allow members to use apps" and select which specific apps that role can access; when an admin enables an app, they can also set action controls (allow all actions, read-only, or a custom action set). All apps are disabled by default until an admin turns them on. The Global Admin Console is a newer, separate beta surface with its own Global admin role and an Access tab for centralizing SSO, domain, and external-application access across workspaces. This is workspace/role-level RBAC over apps and connectors, not permissions scoped to individual Agent Builder workflows.
Журнал аудита
AACFlow
(источник: AACFlow codebase: auditLog table, откроется в новой вкладке)Yes: dedicated audit_log table plus workflow execution logs, exposed via a public /v1/audit-logs API (Enterprise plan), plus continuous SIEM/warehouse export to Datadog, S3, GCS, Azure Blob, BigQuery, or Snowflake via a data-drains dispatcher
OpenAI AgentKit
(источник: Admin and Audit Logs API for the API Platform | OpenAI Help Center, откроется в новой вкладке)Yes, at the platform level. An Admin/Audit Logs API covers the API Platform (API key creation, role changes, login attempts, project changes), and a separate Compliance Logs Platform covers ChatGPT Enterprise/Edu workspaces (conversations, file uploads, admin actions, auth events, agent activity). No source ties audit logging specifically to individual Agent Builder workflow runs.. OpenAI provides an Admin/Audit Logs API for the API Platform and a Compliance Logs Platform for ChatGPT Enterprise/Edu workspaces, covering admin actions, authentication events, and agent activity broadly, but no documentation confirms audit logging scoped specifically to Agent Builder workflow executions.
Дополнительное соответствие требованиям
AACFlow
None claimed (источник: AACFlow Enterprise Page, откроется в новой вкладке)None claimed. No additional third-party certification is claimed.
OpenAI AgentKit
FedRAMP Moderate, PCI DSS, SOC 2, ISO 27001/27701, HIPAA BAA (источник: ChatGPT Enterprise and API Platform | FedRAMP Marketplace, откроется в новой вкладке)FedRAMP Moderate Authorization (ChatGPT Enterprise and API Platform), PCI DSS v4.0.1, SOC 2 Type 2, ISO/IEC 27001:2022, ISO/IEC 27701:2019; supports customer HIPAA compliance via BAA and GDPR/CCPA via DPA; FERPA covered via a separate Student Data Privacy Agreement for ChatGPT Edu. OpenAI's ChatGPT Enterprise and API Platform hold FedRAMP Moderate (Class C) authorization per the FedRAMP Marketplace listing. OpenAI's trust portal lists PCI DSS v4.0.1 for payment-processing components, a SOC 2 Type 2 examination (Security, Availability, Confidentiality, Privacy criteria) covering the API Platform, ChatGPT Enterprise, ChatGPT Edu, and ChatGPT Team, plus ISO/IEC 27001:2022, 27017:2015, 27018:2019, and 27701:2019 certifications, and lists GDPR and CCPA. OpenAI offers a Data Processing Addendum for GDPR/CCPA and a Business Associate Agreement for HIPAA-regulated customers on ChatGPT Enterprise/Edu and the API (not standard ChatGPT Business); this is enablement rather than OpenAI itself being HIPAA-certified, since HIPAA has no formal certification body. FERPA compliance for ChatGPT Edu/for Teachers runs through a separate Student Data Privacy Agreement rather than the general DPA.
Управление моделями и инструментами
AACFlow
(источник: AACFlow codebase: PermissionGroupConfig (allowedModelProviders, deniedModels, deniedTools), откроется в новой вкладке)Yes: enterprise "permission groups" let an admin allow-list/deny-list specific LLM providers and models, and separately deny specific tools/integrations (or disable all MCP or custom tools) per group, layered on top of workspace admin/write/read roles. This does not control whether an LLM provider retains prompts. AACFlow offers no "zero data retention" mode or governed AI gateway. A separate, Enterprise-gated feature lets orgs set a log-retention window and redact PII, but that only controls how long AACFlow itself keeps execution logs.
OpenAI AgentKit
Not publicly documentedUnknown. Not publicly documented in available vendor sources.
Управление учётными данными
AACFlow
(источник: AACFlow Docs: Roles and Permissions, откроется в новой вкладке)Yes: shared credentials (connected accounts, service accounts, workspace secrets) are their own nested permission level (Member/Admin) below organization and workspace roles, and enterprise permission groups can further allow-list specific integrations and restrict which file-share auth modes (public/password/email/SSO) a group may use. A user's personal environment variables/secrets are never shared or inherited by anyone, including org owners/admins.
OpenAI AgentKit
(источник: RBAC | OpenAI Help Center, откроется в новой вкладке)Yes: ChatGPT Enterprise/Business workspaces support role-based access control (RBAC) that restricts which connectors/apps (and by extension their underlying stored credentials) a given custom role or permission group may use, per-app and per-role, with all apps disabled by default until an admin enables them for specific roles.. Granularity is at the connector/app level (e.g. this role may use Google Drive, that role may not) rather than restricting individual named credential instances within a connector type.
Единый вход (SSO)
AACFlow
(источник: AACFlow Docs: Single Sign-On (SSO), откроется в новой вкладке)Yes: SAML 2.0 and OIDC single sign-on, with users routed to SSO by their email domain, plus SCIM 2.0 directory provisioning for Okta, Microsoft Entra ID, OneLogin, and JumpCloud that creates, updates, deactivates, and removes members and maps pushed groups to permission groups, workspace access, and the organization admin role
OpenAI AgentKit
(источник: Configuring SSO | OpenAI Help Center, откроется в новой вкладке)Yes: OpenAI supports SAML-based SSO for ChatGPT Enterprise/Edu/Business and the API Platform, with organization auto-provisioning available either via Automatic Account Creation (email-domain matched invitations) or SCIM-based Directory Sync that invites users based on Identity Provider group membership.. Requires prior verification of at least one domain to enable SSO.
Настраиваемая политика сессий
AACFlow
(источник: AACFlow Docs: Session Policies, откроется в новой вкладке)Yes: Enterprise organization owners and admins can set a max session lifetime (1 to 8,760 hours from sign-in, regardless of activity) and an idle timeout (48 to 8,760 hours without activity), applied to every member on every device. Both limits are optional; leaving them empty keeps the default of 30-day sessions that extend automatically while a member stays active. A separate "Sign out all members" action immediately revokes every member session in the organization except the admin's own, for use after a security incident or an offboarding wave. The 48-hour idle floor exists because session activity is recorded at most once per day, so a shorter window could sign out members who are actively working.
OpenAI AgentKit
No documented admin session lifetime or idle timeout (источник: Admin rollout guide | ChatGPT Learn, откроется в новой вкладке)Not publicly documented: OpenAI does not document an admin-configurable session lifetime or inactivity timeout for ChatGPT workspaces or the API Platform. The workspace identity controls it does document are SSO/SAML, domain verification, SCIM provisioning, MFA enforcement through the identity provider, and RBAC, so how often members must re-authenticate is set at the upstream IdP rather than by a policy in OpenAI's admin console.. OpenAI's admin rollout guide and Work admin FAQ enumerate identity, access-governance, and compliance controls without a session-duration or idle-timeout setting, and the Codex authentication documentation describes tokens being refreshed automatically during active use ('Codex refreshes tokens automatically during use before they expire, so active sessions usually continue without requiring another browser login') rather than an absolute cap an admin can shorten. No session policy specific to AgentKit or Agent Builder is published.
Проверенные собственные интеграции
AACFlow
(источник: AACFlow codebase: first-party block directory, откроется в новой вкладке)Yes: every one of AACFlow's 266 blocks is first-party authored and code-reviewed through the standard pull-request process in the main AACFlow repository; there is no public marketplace where an arbitrary third party can publish and have other users install executable tool code without going through AACFlow's own review. Custom code steps run inside AACFlow's own isolated-vm sandbox rather than as an installable third-party skill package, so the supply-chain trust boundary is AACFlow's codebase review, not an open registry.
OpenAI AgentKit
Partial: reviewed first-party catalog, but open MCP server connections (источник: App submission guidelines | Apps SDK | OpenAI Developers, откроется в новой вкладке)Partial: pre-built Connector Registry entries (Dropbox, Google Drive, SharePoint, Teams) and the ChatGPT Apps directory go through OpenAI identity verification and app review, but Agent Builder's MCP node and the Agents SDK can connect to any third-party MCP server with no vendor vetting pipeline documented. OpenAI's own Connector Registry connectors and ChatGPT Apps directory submissions require developer identity verification and pass through an OpenAI app-review process before listing, per the App submission guidelines. But Agent Builder's MCP node and the Agents SDK let a builder point at any hosted MCP server, first-party or community-run, with no OpenAI review of that server's code. This client-only MCP model mirrors the wider MCP ecosystem, where unreviewed community servers have shipped malicious behavior elsewhere (for example, an unofficial third-party Postmark MCP server was found in September 2025 silently BCC'ing all outgoing email to an attacker). No security incident specific to OpenAI's own Connector Registry, Apps directory, or Agent Builder MCP integration has been publicly reported.
Скрытие персональных данных
AACFlow
(источник: AACFlow Docs: Guardrails Block, откроется в новой вкладке)Yes: a Guardrails workflow block detects and blocks or masks PII (30+ entity types across the US, UK, and several other countries) via Microsoft Presidio, in addition to the org-level data-retention PII policy applied to stored data
OpenAI AgentKit
(источник: Safety in building agents | OpenAI API, откроется в новой вкладке)Yes: Agent Builder's Guardrails node includes a built-in PII detection and redaction capability that automatically catches and masks sensitive data (names, phone numbers, account IDs) flowing through a workflow, alongside jailbreak-detection and content-moderation checks, distinct from generic output-validation guardrails.
Настраиваемое хранение данных
AACFlow
(источник: AACFlow Docs: Data Retention, откроется в новой вкладке)Yes: Enterprise orgs can independently configure log retention, soft-deletion cleanup, and Chat/Copilot task cleanup (chats, runs, checkpoints, Inbox tasks) at 1 day to 5 years or Forever, applied org-wide with no per-workspace override
OpenAI AgentKit
(источник: OpenAI Compliance Platform for Enterprise and Edu Customers, откроется в новой вкладке)No: OpenAI's Compliance Logs Platform retains data for a fixed 30 days (not org-configurable), and API Platform audit logs have no fixed retention/TTL at all rather than an admin-adjustable window; there is no documented org-configurable retention setting for Agent Builder workflow execution logs specifically.. Customers wanting longer retention must build their own continuous log-download pipeline rather than set a retention window in the product.
White-label (собственный бренд)
AACFlow
(источник: AACFlow Docs: Whitelabeling, откроется в новой вкладке)Yes: Enterprise orgs can replace the logo, wordmark, brand name, and primary/accent theme colors across the workspace UI with their own
OpenAI AgentKit
(источник: Theming and customization in ChatKit | OpenAI API, откроется в новой вкладке)No: ChatKit (the deployment surface for Agent Builder workflows) only supports surface-level theming, colors, typography, density, and rounded corners, not full white-labeling. Deeper brand replacement, such as changing the chat bubble shape, header layout, or removing OpenAI product identity, requires forking the ChatKit library.. A third-party technical review explicitly notes deep white-label branding is 'impossible without forking the entire ChatKit library.'
Возможности ИИ
AACFlow provides visual and natural-language building across multiple model providers. Agent Builder's visual selector is limited to OpenAI models and is being retired, although the separate Agents SDK can reach other providers through code-level adapters.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Поддержка нескольких LLM
AACFlow
21 providers plus dynamic-resolution aggregators (OpenRouter, LiteLLM, etc.) (источник: AACFlow codebase: PROVIDER_DEFINITIONS, откроется в новой вкладке)21 provider integrations (OpenAI, Anthropic, Google/Gemini, Azure OpenAI, Azure Anthropic, Groq, Cerebras, Mistral, xAI, Bedrock, Vertex, Ollama, OpenRouter, and more), with OpenRouter, LiteLLM, vLLM, and Ollama resolving models dynamically at runtime rather than from a fixed list, so effective model reach extends well beyond the 21 named providers. apps/sim/providers/models.ts defines 21 provider entries.
OpenAI AgentKit
Agent Builder: OpenAI only. Agents SDK: provider-agnostic via adapters (источник: OpenAI API Pricing (model list), откроется в новой вкладке)Agent Builder's Agent node model selector is OpenAI models only (GPT-5 family, e.g. gpt-5.5, gpt-5.4, gpt-5.4-mini); the separate, code-first Agents SDK is provider-agnostic, with built-in extension points plus best-effort beta LiteLLM/Any-LLM adapters covering 100+ providers (Anthropic, Google, Mistral, and others). Agent Builder's visual canvas only lets you pick from OpenAI's own model lineup. The Agents SDK is a different product: it ships official, built-in provider-integration points (set_default_openai_client, a custom ModelProvider, or per-agent Agent.model) for calling any OpenAI-compatible endpoint, plus best-effort beta adapters for LiteLLM and Any-LLM that route to 100+ non-OpenAI providers. OpenAI's own docs note that adapters add a compatibility layer, so feature support and request semantics can vary by provider and should be validated independently.
Блоки рассуждений агента
AACFlow
(источник: AACFlow codebase: block registry, откроется в новой вкладке)Yes: dedicated agent, function-calling, RAG, code-execution, and evaluation blocks, not just data routing
OpenAI AgentKit
(источник: OpenAI Cookbook: AgentKit walkthrough, откроется в новой вкладке)Yes: dedicated agent/reasoning nodes distinct from plain data routing. Agent Builder's canvas included distinct node types for agents, tools, and logic, versus simple data-passing nodes, supporting multi-agent workflows with typed inputs/outputs.
Создание на естественном языке
AACFlow
(источник: AACFlow Docs: Copilot, откроется в новой вкладке)Yes: Chat + in-editor AI Copilot can build and modify workflows from natural-language requests
OpenAI AgentKit
Not publicly documentedUnknown. No primary OpenAI source describes a chat-to-build / natural-language-to-workflow generation feature within Agent Builder itself, distinct from agents' own natural-language capabilities at runtime.
База знаний / RAG
AACFlow
(источник: AACFlow codebase: KB schema (pgvector + tsvector), откроется в новой вкладке)Yes: hybrid vector (pgvector) plus full-text (tsvector) search knowledge base, 11 supported file formats (csv, doc, docx, html, json, md, pdf, pptx, txt, xlsx, yaml), configurable chunking, plus 51 connectors that continuously sync external sources (Google Drive, Confluence, Slack, Gmail, GitHub, HubSpot, Linear, Jira, and more) into the knowledge base rather than a one-shot upload
OpenAI AgentKit
(источник: OpenAI API Pricing, откроется в новой вкладке)Yes: File Search tool provides built-in vector-store-backed retrieval. File Search is billed at $0.10/GB-day storage (1 GB free) plus $2.50 per 1,000 tool calls, giving Agent Builder and Agents SDK workflows a built-in RAG/file-retrieval capability.
Поддержка MCP
AACFlow
(источник: AACFlow Docs: Using MCP Tools, откроется в новой вкладке)Yes: both MCP client (call external MCP servers) and MCP server (expose AACFlow workflows as MCP tools)
OpenAI AgentKit
(источник: Introducing AgentKit (via search excerpt), откроется в новой вкладке)Yes: Agent Builder supports hosted MCP servers as tools. Agent Builder supports MCP servers, letting an agent use any hosted MCP server to take real-world actions, and the Connector Registry also lists third-party MCPs.
Оценка и ограничители
AACFlow
LLM-judge Evaluator plus Guardrails validation block (источник: AACFlow Docs: Evaluator Block, откроется в новой вкладке)Evaluator block (LLM-judge scoring against user-defined named metrics) and Guardrails block (JSON validity, regex, RAG/hallucination scoring, PII detection/masking). These are per-call scoring/validation primitives, not a batch golden-dataset eval-suite runner or A/B prompt-testing harness.
OpenAI AgentKit
(источник: Introducing AgentKit (via search excerpt), откроется в новой вкладке)Yes: Evals (datasets, trace grading, automated prompt optimization) and a separate open-source Guardrails layer, but Evals is being deprecated alongside Agent Builder. AgentKit shipped Datasets, Trace grading, and Automated prompt optimization under Evals, plus an open-source modular Guardrails safety layer (PII masking, jailbreak detection). Evals is being retired alongside Agent Builder.
Участие человека (human-in-the-loop)
AACFlow
(источник: AACFlow Docs: Human in the Loop Block, откроется в новой вкладке)Yes: dedicated approval block that pauses a run and waits for a human-submitted "Resume Form," with durable pause/resume via persisted execution snapshots and notification hooks (e.g. Slack, email) carrying the resume link
OpenAI AgentKit
(источник: Agent Builder: Node reference (Human approval node), откроется в новой вкладке)Yes: dedicated 'Human approval' node in Agent Builder; SDK-level tool-approval interrupts in Agents SDK. Agent Builder has a first-class Human approval logic node that lets a workflow pause for a person to approve or reject a step before continuing (e.g., approve/reject an agent-drafted email before an MCP node sends it). At the SDK level, tool calls flagged as needing approval pause the run and surface as a pending interruption, then resume from saved state once the developer approves or rejects it. There's no built-in approver-notification channel (no native email/Slack alert); the surrounding app has to present the pending approval itself, though the resume mechanism is native.
Генеративные медиа
AACFlow
(источник: AACFlow codebase: Image Generator V2, откроется в новой вкладке)Yes: dedicated image (3 provider families incl. OpenAI, Gemini, Fal.ai proxy), video (5 provider families incl. Runway, Veo, Luma, Hailuo, Fal.ai proxy), text-to-speech (7 providers), and speech-to-text (5 providers) blocks
OpenAI AgentKit
Image generation only, via tool call (источник: Agent Builder: Node reference, откроется в новой вкладке)Image generation only, via tool call; no built-in video or audio (TTS/STT) generation node. Agent Builder's node palette (Start, Agent, Note, File search, Guardrails, MCP, If/else, While, Human approval, Transform, Set state) has no dedicated image/video/audio node. Agents can invoke OpenAI's separate image generation tool (GPT Image models) as a tool call. Audio (Whisper transcription/TTS) and video (Sora) are separate OpenAI API products, not surfaced as canvas nodes. No third-party media-gen providers are wired in as nodes.
Динамическое использование инструментов
AACFlow
(источник: AACFlow codebase: agent tool resolution (pre-wired only), откроется в новой вкладке)No: an Agent block calls tools the workflow author explicitly added to it at build time, rather than browsing and picking from a broader pool (e.g. an entire MCP server catalog) at inference time. Runtime MCP "discovery" exists to resolve/refresh the schema of an already-configured tool. The model does not browse or choose from the server's full tool list.
OpenAI AgentKit
Not publicly documentedUnknown. Not publicly documented in available vendor sources.
Автоматическая замена модели
AACFlow
(источник: AACFlow codebase: executeProviderRequest (no retry/fallback), откроется в новой вкладке)No: a failed or rate-limited LLM call is retried using AACFlow's own hosted API keys for the same model, rather than automatically switching to a different model or provider. A "fallback" comment in the provider layer refers to rotating among AACFlow's own hosted API keys for the same model, not switching models.
OpenAI AgentKit
Not publicly documentedUnknown. Not publicly documented in available vendor sources.
Навыки агентов
AACFlow
(источник: AACFlow Docs: Agent skills, откроется в новой вкладке)Yes: named, reusable "Agent Skills" (built on the open Agent Skills / SKILL.md format) that agents load on demand via progressive disclosure, editable in-app or imported from a SKILL.md file or GitHub URL. Only the skill name and description sit in the agent's system prompt (~50-100 tokens each); the full instructions load into context only when the agent calls load_skill.
OpenAI AgentKit
(источник: Prompt engineering | OpenAI API, откроется в новой вкладке)No: Agent Builder/AgentKit has no dedicated feature for defining a reusable, named prompt or knowledge snippet that multiple agents can share by reference. A distinct 'Agent Skills' concept exists only in the unrelated Codex product line, not in AgentKit.. OpenAI recommends migrating reusable prompts to code-managed, versioned helper files instead, which is the opposite direction of a built-in skills feature.
Встроенное развёртывание чата
AACFlow
(источник: AACFlow Docs: Chat Deployment, откроется в новой вкладке)Yes: a workflow can be deployed as a public, shareable Chat interface with selectable auth (public, password, email OTP, or SSO), in addition to API and MCP deployment targets
OpenAI AgentKit
(источник: ChatKit | OpenAI API, откроется в новой вкладке)Yes: ChatKit is a native toolkit for embedding a publicly deployable, customizable chat-based agent surface (web widget) backed by a published Agent Builder workflow ID or the Agents SDK, distinct from just a form/API/webhook target.. ChatKit remains available even as Agent Builder itself is being wound down.
Параллельное выполнение
AACFlow
(источник: AACFlow Docs: Parallel block, откроется в новой вкладке)Yes: a native Parallel block fans a run out into concurrent branches (fixed count or one per list item) and joins their results back into the workflow automatically. Contained blocks run concurrently instead of sequentially, either a fixed number of times or once per item in a list/collection, and each branch's output aggregates for downstream blocks.
OpenAI AgentKit
(источник: Agent Builder: Node reference, откроется в новой вкладке)No dedicated node in the visual Agent Builder canvas. Its node palette (Start, Agent, Note, File search, Guardrails, MCP, If/else, While, Human approval, Transform, Set state) has no fan-out/fan-in or 'parallel branches' node; If/else and While are the only branching/looping constructs, and both execute sequentially. Concurrent multi-agent execution requires writing code against the separate Agents SDK (e.g. Python asyncio to run agents in parallel and merge results), not the no-code builder.. OpenAI developer community threads on Agent Builder confirm the canvas lacks a fan-out block and point developers to the Agents SDK for true concurrent branch execution.
Протокол Agent2Agent (A2A)
AACFlow
(источник: AACFlow Docs: A2A integration, откроется в новой вкладке)Yes: a dedicated A2A block sends messages to, tracks and cancels tasks on, and discovers the capabilities of any Agent2Agent (A2A)-compliant external agent via its Agent Card
OpenAI AgentKit
(источник: Introducing AgentKit (via search excerpt), откроется в новой вкладке)No: not documented as supported by AgentKit or the Agents SDK. No OpenAI documentation, changelog, or product page for AgentKit, Agent Builder, or the Agents SDK describes support for the Agent2Agent (A2A) protocol or Agent Cards. A2A is an open standard originated by Google and now under the Linux Foundation; OpenAI's own interoperability story is built around MCP (tool-calling) rather than A2A peer-to-peer agent discovery.
Блок цикла / итерации
AACFlow
(источник: AACFlow Docs: Loop block, откроется в новой вкладке)Yes: a Loop container block runs the blocks inside it repeatedly (For a fixed count, ForEach over a collection, While a condition holds, or Do-While), running iterations one after another; concurrent fan-out is a separate Parallel block
OpenAI AgentKit
(источник: Node reference | OpenAI API, откроется в новой вкладке)Yes: Agent Builder has a dedicated 'While' logic node that loops on a custom Common Expression Language (CEL) condition, re-running the connected steps sequentially each pass until the condition is false.. The While node is condition-based rather than an explicit for-each-over-a-list container: iterating over a list means writing a CEL expression that checks an index or remaining-items condition against a Set-state variable, and incrementing that variable each pass, rather than dropping in a purpose-built for-each block. Iterations run one after another (sequential), matching the node palette's lack of any fan-out/parallel node.
Интеграции
AACFlow publishes integration and trigger counts for its first-party automation catalog, while OpenAI combines a smaller documented connector set with access to external MCP servers, which are third-party endpoints OpenAI does not review.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Интеграции
AACFlow
1,000+ integrations (266 blocks, ~3,900 tool actions) (источник: AACFlow codebase: BLOCK_REGISTRY, откроется в новой вкладке)1,000+ integrations counting individual API actions, built from 266 first-party blocks and roughly 3,900 underlying tool actions. AACFlow's landing page cites the "1,000+ integrations" figure; the block/tool-action counts are the same integration surface measured at a different level of granularity.
OpenAI AgentKit
No published total connector count (источник: Introducing AgentKit (via search excerpt), откроется в новой вкладке)Unknown exact count. OpenAI names specific pre-built connectors (Dropbox, Google Drive, SharePoint, Microsoft Teams) plus support for arbitrary third-party MCP servers, but publishes no total integration/connector count comparable to a competitor's marketed number.
Типы триггеров
AACFlow
Webhook, cron, chat, REST API, 61 app triggers, plus a diff-aware Tables trigger (источник: AACFlow Docs: Triggers overview, откроется в новой вкладке)Webhook, schedule/cron, chat, REST API, and event-based triggers for 61 apps (Slack, Gmail, GitHub, Stripe, etc.), plus a native row-level trigger on AACFlow Tables that fires on insert/update with an optional column watch-list and emits a before/after diff
OpenAI AgentKit
Not comprehensively documentedUnknown / not comprehensively documented. Primary sources describe workflow execution via API calls and ChatKit chat interfaces; no vendor page enumerates trigger types (webhook, schedule, app-event) the way a workflow-automation product typically does.
Шаги с собственным кодом
AACFlow
(источник: AACFlow Docs: Function block, откроется в новой вкладке)Yes: code-execution block for custom logic
OpenAI AgentKit
(источник: OpenAI API: Agents SDK guide, откроется в новой вкладке)Yes, effectively. The Agents SDK is itself Python/TypeScript code, and Agent Builder workflows can call custom tools/functions. Because the long-term supported path is the code-first Agents SDK (Python and TypeScript), custom code isn't a step type bolted onto a no-code canvas. It's the native building block itself.
Настраиваемые песочницы для кода
AACFlow
(источник: AACFlow Docs: Function block - Sandboxes, откроется в новой вкладке)Yes: named sandboxes a workspace maintains and a Function block selects, each declaring a language, its pip or npm dependencies, optional Debian/APT system packages, and optional managed CLI tools from a catalog grouped by cloud, Kubernetes, infrastructure, deployment, data and storage, and security tools; on aacflow.io they require an active Max or Enterprise plan. Only workspace admins can create or edit sandboxes, in Settings → Sandboxes. On aacflow.io each specification is prebuilt into a reusable image so runs pay no install cost. Two sandboxes with the same language, dependency list, system packages, and managed CLI tools share one build. Every managed CLI entry uses a pinned, integrity-checked vendor artifact. With no sandbox selected, remote code runs on the dedicated Function base; import-free JavaScript stays in the local isolated runtime and ignores the sandbox selection either way.
OpenAI AgentKit
Agents SDK sandbox image only; Code Interpreter is fixed (источник: Sandbox agents | OpenAI API, откроется в новой вкладке)Partial: configurable only on the code-first path. The Agents SDK's sandbox agents let you name the container image the agent's shell and code run in (the documented Docker example passes image: 'node:22-bookworm-slim' to DockerSandboxClient), so third-party packages, OS packages, and CLI binaries come from an image you build and control. The hosted Code Interpreter tool is the opposite: a fixed OpenAI-managed container whose only user-adjustable setting is the memory tier (1g default, 4g, 16g, 64g), with no documented way to declare pip/npm or system packages.. Sandbox execution runs on infrastructure you supply, not OpenAI's: the documented clients are UnixLocalSandboxClient (macOS/Linux) and DockerSandboxClient for local execution, plus hosted providers via BlaxelSandboxClient, CloudflareSandboxClient, DaytonaSandboxClient, E2BSandboxClient, ModalSandboxClient, RunloopSandboxClient, and VercelSandboxClient. The visual Agent Builder canvas is unaffected either way: its node palette (Start, Agent, Note, File search, Guardrails, MCP, If/else, While, Human approval, Transform, Set state) has no code node, so a no-code builder's only code-execution surface is the fixed Code Interpreter container, which also discards all its data 20 minutes after last use.
Развёртывание через API
AACFlow
(источник: AACFlow Docs: API Reference - Getting Started, откроется в новой вкладке)Yes: a public REST API (mostly under /api/, with /api/v1 reserved for logs and audit-log endpoints) supporting API-triggered workflow execution and deployment rollback. The API reference does not document SSE streaming, a resumable event buffer, a dedicated API-trigger block, or a chat-deployment surface as part of the REST API itself.
OpenAI AgentKit
(источник: OpenAI API: Agents SDK guide, откроется в новой вкладке)Yes: agents/workflows are consumed via the OpenAI API and can be embedded via ChatKit; Agent Builder itself is not a customer-facing REST API generator. Agents built with the Agents SDK run as regular application code that developers expose via their own APIs; ChatKit provides an embeddable chat surface rather than an auto-generated REST endpoint for a visual workflow.
SDK и расширяемость
AACFlow
Official Python and TypeScript SDKs, plus MCP, code block, and A2A protocol (источник: AACFlow Docs: Python SDK, откроется в новой вкладке)Official client SDKs exist for Python (aacflow-sdk, pip install aacflow-sdk) and TypeScript/JavaScript (aacflow-sdk, npm install aacflow-sdk), both wrapping the REST API (x-api-key header) with methods like execute_workflow / executeWorkflow, retry-with-backoff, and usage-limit lookups. Extensibility is further extended by MCP (client + server), a sandboxed code-execution block (JS/Python), custom tools, and an Agent-to-Agent (A2A) protocol block for external agent interop
OpenAI AgentKit
Agents SDK, Apps SDK, and app directory (источник: Agents SDK guide, откроется в новой вкладке)Official Agents SDK (Python + TypeScript/JS); Apps SDK (MCP-based) for building integrations; ChatGPT Apps directory as a community marketplace. Agents SDK ships as open-source client libraries for Python (openai-agents-python) and TypeScript/JavaScript (openai-agents-js). It defaults to OpenAI's own Responses/Chat Completions APIs but is provider-agnostic in practice: built-in provider-integration points plus best-effort beta LiteLLM/Any-LLM adapters let it call 100+ non-OpenAI providers (this is a code-level capability, distinct from Agent Builder's OpenAI-only model selector). Custom integrations are built as MCP servers using the Apps SDK, an open standard on the Model Context Protocol; Agent Builder's MCP node connects to any third-party MCP server. A Connector Registry centralizes admin-managed connectors (Dropbox, Google Drive, SharePoint, Teams) plus third-party MCPs. Community apps go through a dashboard-based submission and review flow and, once approved, are listed in the ChatGPT Apps directory.
Публикация как MCP-сервер
AACFlow
(источник: AACFlow Docs: MCP Deployment, откроется в новой вкладке)Yes: any deployed workflow can be published as a tool on an MCP server (private, API-key protected, or public/no-auth), with ready-to-paste client config generated for Codex, Cursor, Claude Code, Claude Desktop, and VS Code
OpenAI AgentKit
(источник: 8 best MCP servers to build production-ready agents in OpenAI Agent Builder, откроется в новой вкладке)No: publicly available evidence only shows AgentKit/Agent Builder consuming external MCP servers as tools (adding an MCP button and pointing it at OpenAI's or third-party MCP servers). There is no documented feature to publish a deployed Agent Builder workflow itself as a callable MCP server for external AI tools to consume.. A separate OpenAI product, the Apps SDK, discusses exposing an MCP app as a server, but that is not the same as publishing an Agent Builder workflow as an MCP server.
Наблюдаемость и надёжность
Both products provide run tracing, but their operational models differ. AACFlow includes visual workflow alerts and error branches, while several OpenAI retry, checkpoint, and recovery capabilities require developers to configure the Agents SDK in code.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Трассировка и наблюдаемость
AACFlow
(источник: AACFlow codebase: TraceSpan tree builder, откроется в новой вкладке)Yes: execution logs include a per-block/per-span trace view (duration, cost, token counts, and latency stats like TTFT/TPS) with expandable nested iteration groups, plus a "View Snapshot" frozen copy of the workflow structure and block states at run time for debugging. This trace view is built directly into AACFlow rather than a raw export browsable in an external tool like Jaeger, and does not expose aggregate latency-percentile charts (p50/p95/p99). The run snapshot serves as a log-detail/debugging artifact rather than a resumable mid-run checkpoint.
OpenAI AgentKit
(источник: Agents SDK: Integrations and observability, откроется в новой вкладке)Yes: per-run tracing with spans (model calls, tool calls, handoffs, guardrails, custom spans) in a customer-facing Traces dashboard; no dedicated metrics dashboard (latency percentiles/error rates) documented. Tracing is on by default in the Agents SDK. Every run produces a structured trace with an ID, an optional group ID, and metadata tags, viewable in the Traces dashboard (Logs > Traces) for debugging and, via trace grading/agent evals, benchmarking. There's no aggregate metrics dashboard surfacing latency percentiles or error-rate trends across runs: official docs cover single-run trace inspection plus eval-based benchmarking, not a fleet-wide metrics view.
Надёжность и повторные попытки
AACFlow
Tool-call retries (up to 10x); single-attempt job orchestration (источник: AACFlow codebase: ToolRetryConfig (exponential backoff), откроется в новой вкладке)Individual tool/API calls have configurable exponential-backoff retry (up to 10 attempts). The background job-orchestration layer itself retries only once by design. Durability instead comes from consecutive-failure tracking on schedules and the human-in-the-loop snapshot pause/resume mechanism. AACFlow does not offer guaranteed-once-only block execution, a failed-run holding queue for manual recovery, or a "replay a past execution with its original inputs" feature. The per-execution debugging snapshot serves as a log-detail artifact rather than a resumable mid-run checkpoint.
OpenAI AgentKit
Opt-in retries and checkpoint/resume (источник: OpenAI Agents SDK: Running agents, откроется в новой вкладке)Opt-in retries, SDK-level checkpointing/resume of run state, but no one-click replay of a past production execution with original inputs from the Agent Builder UI. The Agents SDK supports configurable automatic retries on transient failures (network errors, rate limits, server errors), off by default and requiring an explicit retry policy. The SDK also records each run's execution state so it can resume after an interruption (e.g., pending tool approval) or a process restart, giving checkpoint/resume for fault tolerance. This is a developer-invoked mechanism in code, not a dashboard 'replay this failed execution' button, and there's no UI-driven replay-with-original-inputs feature for past runs.
Оповещения о сбоях
AACFlow
(источник: AACFlow Docs: AACFlow Workspace Events trigger, откроется в новой вкладке)Yes: a sim_workspace_event trigger fires on run success/failure, deployments, and cost/latency spikes, wired to any notification block (Slack, email, webhook) for real-time alerting
OpenAI AgentKit
(источник: Agents SDK: Integrations and observability, откроется в новой вкладке)No proactive alerting for failed runs or cost/latency thresholds. Traces are pull-based, inspected manually. The Traces dashboard records model calls, tool calls, handoffs, guardrails, and custom spans per run for after-the-fact debugging, but it's a manual inspection tool you open to debug a specific run. There's no built-in push notification (email/Slack/webhook) when a run fails or crosses a cost/latency threshold. Generic OpenAI platform webhooks exist for events like batch or fine-tuning job completion, but these aren't documented as covering Agent Builder/Agents SDK run failures or thresholds.
Выгрузка данных (data drains)
AACFlow
(источник: AACFlow Docs: Data Drains, откроется в новой вкладке)Yes: Enterprise orgs can continuously export workflow logs, job logs, or audit logs on a schedule to a customer-owned S3 bucket, GCS bucket, Azure Blob container, BigQuery table, Snowflake table, Datadog logs intake, or an HTTPS webhook. Each drain exports exactly one data source; multiple drains are created to export multiple sources. Viewing drain config/run history is restricted to org owners/admins.
OpenAI AgentKit
(источник: OpenAI Compliance Platform for Enterprise and Edu Customers, откроется в новой вкладке)Yes: OpenAI's Compliance Logs Platform and Admin/Audit Logs API continuously export execution, audit, and usage data as immutable, time-windowed JSONL log files, with 13 pre-built turnkey integrations to eDiscovery, DLP, and SIEM vendors (e.g. CrowdStrike, GlobalRelay), beyond just viewing logs in-product.. This is an org-wide ChatGPT Enterprise/API Platform compliance feature, not something scoped specifically to Agent Builder workflow runs.
Асинхронное выполнение
AACFlow
(источник: AACFlow codebase: async execution handler, откроется в новой вкладке)Yes: a workflow can be triggered in fire-and-forget async mode, returning HTTP 202 with an execution ID immediately, then polled through the canonical execution resource across queued/running/terminal states. Async runs are tracked by execution ID through the same execution status endpoint used for durable logs rather than a separate queue-job resource.
OpenAI AgentKit
(источник: OpenAI: Background mode guide, откроется в новой вкладке)Yes: OpenAI's platform supports a background mode that flags a Responses API call to run asynchronously instead of blocking. The client immediately gets back a response ID marked "queued" and polls a status endpoint until the run reaches a terminal state like completed or failed.. Background mode is a platform-level Responses API feature (used by Agents SDK/AgentKit flows), not unique to the Agent Builder canvas UI itself; an in-flight response can also be cancelled directly. Response data is retained only about 10 minutes for polling, and it is incompatible with Zero Data Retention projects.
Лимиты выполнения
AACFlow
5-50 min sync; async defaults to 90 min, Enterprise up to 7 days (источник: AACFlow Docs: Concurrent Executions, откроется в новой вкладке)Plan-gated: synchronous runs time out at 5 minutes on accounts without a plan and 50 minutes on paid plans; async runs default to 90 minutes, while Enterprise policy can be configured up to 7 days; concurrency ranges from 10 to 1,000 executions per billing account depending on plan. A direct async API request can shorten the account policy for that request, but cannot extend it. Concurrency limits are published in the platform cost docs, where the Enterprise limit is 1,000 by default and customizable. A run that exceeds its time limit is terminated and marked failed with a timeout error.
OpenAI AgentKit
No published AgentKit-specific run/concurrency caps (источник: OpenAI: Rate limits guide (usage tiers, RPM/TPM/RPD/TPD, vector store 300 rpm), откроется в новой вкладке)Unknown: OpenAI does not publish a fixed maximum duration for a single Agent Builder workflow run or Agents SDK execution, nor a concurrency cap specific to AgentKit. The only concrete numbers found are general API usage-tier limits (requests and tokens per minute/day, scaling from a $100/month allowance at Tier 1 up to $200,000/month at Tier 5) and a 300-requests-per-minute cap per vector store for file ingestion endpoints.. Background mode responses are only retained about 10 minutes for polling, a practical window for checking back on a run, but not a documented hard execution timeout. The one concrete node-level timeout is the Agent Builder Approval node, which times out after 5 minutes and alerts a supervisor if unactioned. Actual RPM/TPM caps are account/model-specific and only visible in the OpenAI dashboard.
Обработка частичных сбоев
AACFlow
(источник: AACFlow codebase: error-output edge routing, откроется в новой вкладке)Yes: any block can be wired to a dedicated error-output edge, so a failing step routes execution down an error-handling branch instead of always halting the entire run
OpenAI AgentKit
(источник: OpenAI: Agent Builder node reference (Guardrails, If/Else, Human Approval nodes), откроется в новой вкладке)No: Agent Builder has no dedicated try/catch or fallback-path construct for a failing step. Error handling has to be built manually with a Guardrails node (a pass/fail checkpoint on a prior node's output) combined with If/Else logic nodes to branch on conditions. OpenAI's own guidance for a guardrail failure is to end the workflow or loop back to the previous step, not to continue the rest of the run on a separate error path.. Guardrails nodes and If/Else logic nodes can be composed to approximate conditional routing around a failure, and a Human Approval node can pause for intervention, but none of these work as an automatic "catch this failing step and keep the rest of the run going" mechanism the way a dedicated error-handling path would.
Выполнение без присмотра
AACFlow
(источник: AACFlow codebase: trigger.dev background job backend, откроется в новой вкладке)Yes: scheduled, webhook, and chat-triggered runs execute as background jobs on trigger.dev workers, entirely on AACFlow's servers. No client device needs to be open, awake, or connected for a run to fire or complete; closing the browser tab or shutting down a laptop has no effect on a scheduled or triggered workflow.
OpenAI AgentKit
(источник: Node reference | OpenAI API, откроется в новой вкладке)No native scheduler ships with AgentKit; a scheduled or triggered run only executes with zero dependency on a client device if the developer deploys their own Agents SDK code on always-on server or serverless infrastructure themselves. Agent Builder's own trigger surface covers API calls and ChatKit chat sessions, not a built-in cron/schedule trigger. Neither Agent Builder's node reference nor its documented trigger types include a schedule/cron trigger; time-based, run-without-a-human execution is described for a separate product, ChatGPT Workspace Agents, not AgentKit. Because Agents SDK code is ordinary Python/TypeScript, whether a run survives a closed laptop or a disconnected client depends entirely on where the developer hosts that code (e.g. AWS Lambda, a container, or a cron-triggered server process) and whether they add a third-party durability layer, such as Temporal, Dapr, Restate, or DBOS, for crash recovery and long-running execution. There is no first-party, always-on worker fleet or scheduler bundled with AgentKit itself.
Поддержка
OpenAI documents 24/7 support and service commitments for qualifying enterprise offerings, while AACFlow lists dedicated Enterprise support without publishing response-time or uptime terms. Buyers who require contractual guarantees should confirm the exact coverage with each vendor.
CompareAACFlow vs OpenAI AgentKit
AACFlow
OpenAI AgentKit
Каналы поддержки
AACFlow
Community support plus Enterprise 'Dedicated Support' (источник: AACFlow Pricing Page, откроется в новой вкладке)Community plus an unquantified "Dedicated Support" flag on the Enterprise plan. Enterprise and pricing pages do not include CSM, onboarding/enablement, or professional-services details beyond a plan-comparison-table "Dedicated Support" flag.
OpenAI AgentKit
Community forum plus 24/7 enterprise support (источник: OpenAI Help Center: How can I contact support?, откроется в новой вкладке)Community forum (community.openai.com), help center articles, and enterprise sales-led support; ChatGPT Enterprise includes 24/7 support. OpenAI's Help Center documents standard support channels, and ChatGPT Enterprise plans include 24/7 support with SLAs.
SLA
AACFlow
(источник: AACFlow Pricing Page, откроется в новой вкладке)Yes: the Enterprise plan includes a "Dedicated Support" feature per the pricing plan-comparison table; no SLA terminology, response-time, or uptime figures are published on the enterprise or pricing pages
OpenAI AgentKit
(источник: Scale Tier for API Customers, откроется в новой вкладке)Yes, for enterprise/Scale Tier customers. E.g., 99.9% uptime SLA on Scale Tier, and priority-processing SLAs with service credits. Scale Tier traffic offers a 99.9% uptime SLA with prioritized compute (available to Enterprise customers); Priority Processing customers on enterprise agreements can receive service credits if SLAs are missed. Exact SLA terms require contacting OpenAI sales.
Сообщество
AACFlow
(источник: AACFlow Landing Page, откроется в новой вкладке)No community size is published yet
OpenAI AgentKit
27,500+ GitHub stars on Agents SDK (источник: GitHub API: openai/openai-agents-python, откроется в новой вкладке)Over 27,500 GitHub stars on the companion open-source Agents SDK (openai/openai-agents-python) as of 2026-07-02. A direct GitHub API check confirms roughly 27,600 stargazers for openai/openai-agents-python. This measures the Agents SDK's community, not Agent Builder/AgentKit specifically, since AgentKit's GUI components are closed-source SaaS.
Академия / обучение
AACFlow
(источник: AACFlow Docs: Academy, откроется в новой вкладке)Yes: AACFlow Academy is a dedicated structured-learning section of the docs site, separate from reference documentation and the API reference
OpenAI AgentKit
(источник: OpenAI Academy, откроется в новой вкладке)Yes: OpenAI Academy offers structured, free self-paced courses (AI Foundations, Applied AI Foundations, Agents and Workflows) plus official OpenAI Certifications (e.g. the AI Foundations certification backed by ETS and Credly), going beyond ad hoc docs or blog content.. Academy and Certifications are separate programs; course-completion certificates are not the same as formal OpenAI Certifications. This is a company-wide OpenAI offering, not specific to Agent Builder/AgentKit.
Сильные стороны AACFlow
AI Copilot / Chat agent-building surface (источник: AACFlow Docs: Copilot, откроется в новой вкладке)
Chat builds and manages work across the workspace; in-editor Copilot edits a single workflow.
A workspace-wide natural-language surface (Chat) that can build workflows, manage data, and take actions across integrations, plus an in-editor Copilot scoped to building and editing a single workflow directly.Hybrid semantic + keyword knowledge base (источник: AACFlow codebase: KB schema + file-parsers, откроется в новой вкладке)
Combines vector and full-text search with configurable chunking across 11 file formats.
Built-in RAG with pgvector embeddings and a generated tsvector column for combined vector + full-text search, plus a token-based chunker with configurable chunk size/overlap and 11 supported file formats (csv, doc, docx, html, json, md, pdf, pptx, txt, xlsx, yaml).Native MCP client and server (источник: AACFlow Docs: MCP Deployment, откроется в новой вкладке)
Call external MCP servers as tools, or expose AACFlow workflows as an MCP server.
A dedicated MCP block lets any workflow call external MCP servers as a tool, and a serve/workflow-servers API surface lets AACFlow expose its own workflows as MCP servers.Fork a workspace into dev, qa, and prod environments (источник: AACFlow Docs: Workspace Forks, откроется в новой вкладке)
Fork, diff, and promote environments with mandatory credential remapping.
Fork a whole workspace into a dev/qa/prod-style child environment, preview a diff, and promote changes bidirectionally. Credential and env-var remapping is required on every promote, so secrets never cross environments silently.Human-in-the-loop approvals with durable resume (источник: AACFlow Docs: Human in the Loop Block, откроется в новой вкладке)
Pause a run for human approval and resume later via a durable snapshot link.
A dedicated block pauses a run and waits for a human-submitted approval form, backed by persisted execution snapshots so the run can resume later via a link, even after a server restart.Live multiplayer canvas editing (источник: AACFlow codebase: realtime presence handler, откроется в новой вкладке)
Real-time cursors, selections, and synced edits on the same canvas.
Real-time cursors, selection broadcasting, and synced concurrent edits over a dedicated realtime backend, so a team can build the same workflow together at the same time.Задокументированные ограничения OpenAI AgentKit
Agent Builder and Evals are being shut down (источник: OpenAI Community: Deprecation notice - Agent Builder, откроется в новой вкладке)
Visual builder and evals platform shut down November 30, 2026.
OpenAI announced in June 2026 that it is winding down Agent Builder (the visual no-code canvas) and the Evals platform. Evals goes read-only October 31, 2026, and both are fully unavailable November 30, 2026. The visual/no-code building experience central to AgentKit as originally announced is being discontinued in favor of the code-first Agents SDK or ChatGPT Workspace Agents.No self-hosted managed backend after winddown (источник: OpenAI Community: Deprecation notice - Agent Builder, откроется в новой вкладке)
Self-hosting requires running ChatKit on your own infrastructure entirely.
Once Agent Builder's managed hosting is discontinued, the only supported ChatKit integration path requires developers to run ChatKit on their own infrastructure via the Python SDK connected to a custom agentic backend. There is no OpenAI-hosted no-code deployment option remaining.Usage-based, per-token/per-call pricing with no published flat plan for AgentKit itself (источник: OpenAI API Pricing, откроется в новой вкладке)
No flat plan; costs scale with token and tool usage.
There is no dedicated AgentKit subscription tier. Costs are the sum of model tokens, Code Interpreter sessions ($0.03-$1.92 per session by memory tier), and File Search ($0.10/GB-day storage plus $2.50 per 1,000 tool calls), which makes cost forecasting harder than AACFlow's published pricing, where a Pro seat is a flat $25/user/month with a monthly credit allowance included, rather than open-ended per-token and per-call metering.Итог
Choose AACFlow if you want an AI workspace that treats AI agents as first-class citizens: native multi-LLM support, real-time multiplayer editing, environment promotion (dev/qa/prod), human-in-the-loop approvals, and enterprise governance (SSO, credential-level permissions, audit logs) built in rather than bolted on.
Choose OpenAI AgentKit if you specifically need an official, open-source Agents SDK wired natively to its own models: The Agents SDK, openai-agents-python, is open source under the MIT license with over 27,500 GitHub stars and natively wired into OpenAI's own model lineup. It's the path OpenAI is steering AgentKit users toward as Agent Builder and Evals wind down, and a team fully committed to an all-OpenAI, code-first stack gets that directly.
Что почитать ещё
Часто задаваемые вопросы
AACFlow is an AI workspace where teams build, deploy, and manage AI agents visually, conversationally, or with code. OpenAI AgentKit bundled a visual Agent Builder, ChatKit embeddable chat UI, Connector Registry, Guardrails, and Evals for building agentic workflows on OpenAI's models. But OpenAI is winding down Agent Builder and Evals, with full shutdown November 30, 2026, in favor of the code-first Agents SDK or ChatGPT Workspace Agents. Teams considering a switch typically weigh pricing model, and how AI-native the platform's agent-building experience is.
