Head to head · Agent frameworks · October 2026 research run
OpenAI Agents SDK vs Terse Durable Actors
OpenAI Agents SDK scores 90 (AA) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 6 of 7 scored categories. Both do agent frameworks.
Best agent frameworks and SDKs · All 190 frameworks comparisons
Which one, for what
Best for Teams that want hand-offs, guardrails and approvals with little code, and are happy with OpenAI's tracing or will turn it off.
Ahead on
- Reliability, 85 against 51
- Schema & documentation, 95 against 81
- Agent ergonomics, 97 against 89
- Security & auth, 80 against 49
- Maintenance & community, 100 against 83
- Transparency & trust, 89 against 53
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
Tracing on by default, with model and tool content, sent to OpenAI
Best for Stateful actors for chat, collaboration and multi-agent coordination, as an open-source alternative to Cloudflare Durable Objects per its README.
Also in its favour
- Free to start without a card
Watch for
Version 0.18.7, with no stable release and no changelog file in the repository
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Transparency & trust OpenAI Agents SDK +36
OpenAI Agents SDK 89
MIT (30). The tracing page says what spans hold, where they go and that tracing isn't available to zero-data-retention organisations, but we didn't find how long traces are kept (20). Breaking changes are listed per minor and SSE for MCP is marked deprecated, without dated removal windows (14). Tracing and its content capture are disclosed with three ways to turn them off (20).
Terse Durable Actors 53
MIT, copyright 2026 Terse (30). Self-hosted state stays in your PostgreSQL database and GCS bucket per the self-hosting guide. Terse's terms and privacy policy, both dated 14 May 2026, describe an earlier product of flows and workspaces, give no retention periods and don't mention Terse Cloud (10 of 30). No deprecation policy found, and SECURITY.md says older releases get no backports (0 of 20). SDK invocation telemetry is off by default and writes to standard error when enabled, and request spans and platform events are exported only to a collector the operator configures. No call to Terse's own hosts was found in the runtime or SDK source (18 of 20). Total 58.
Reliability OpenAI Agents SDK +34
OpenAI Agents SDK 85
Official packages on PyPI (Python 3.10 or newer, requires-python re-read on 1 November) and npm (20). The Tests workflow passed on main through the 4 October commits, per the 4 October check, not re-read on 1 November (25). 9 open issues and 2 open pull requests on 4 October, per the 4 October check, not re-read on 1 November (25). A written policy for 0.Y.Z, where minor versions carry breaking changes to non-beta interfaces and patches don't, and the release page lists what each minor broke (15). 0.23.0 and 0.24.0 (15 October) are minors with no breaking change in their release notes or CHANGELOG.md, and the release page still has no entry for either on 1 November. 0.24.0, still pre-1.0 and still the newest on PyPI on 1 November (0).
Terse Durable Actors 51
Graded as local software, the runtime and SDKs you run yourself. The README and the Python SDK README install with bunx durable-actors or uvx --from 'durable-actors[cli]' and state Bun 1.4.2+ and Python 3.11+, and the release workflow publishes to npm. The registry pages were not read (15 of 20). A public CI workflow runs Rust, Python, TypeScript and example builds on every push and pull request. Whether it passes on main was not checked (15 of 25). 23 issues were open on 18 November 2026, mostly improvements and feature requests, with a few bug reports such as a constructor that keeps its SQLite writes after throwing (17 November) and alarms that run more than once (11 November) (18 of 25). Release notes are generated from pull-request labels on GitHub Releases, which were not read, and no changelog file or breaking-change notes were found in the repository (3 of 15). Version 0.18.7, not 1.0 or declared stable (0). Total 51.
Security & auth OpenAI Agents SDK +31
OpenAI Agents SDK 80
Tracing is on by default and trace_include_sensitive_data defaults to true, so model and function-call inputs and outputs go to OpenAI's Traces dashboard. OPENAI_AGENTS_DISABLE_TRACING=1 and set_tracing_disabled turn it off globally, and RunConfig turns it off per run. Through 0.23.1 the per-run opt-out didn't apply inside the caller's own trace. The fix shipped in 0.24.0 on 15 October (10). Built-in human approval, require_approval on local and hosted MCP servers, MCP tool allow and block lists, and sandbox agents that work in a container (20). Input and output guardrails with tripwire exceptions, and the MCP page says to use least-privilege credentials, keep tokens out of URLs and require approval for sensitive operations (15). Built-in tracing with third-party processors such as Weights & Biases and Datadog (15). SECURITY.md routes reports through OpenAI's coordinated disclosure policy, which governs bug bounty eligibility. OSV listed no advisories for openai-agents on PyPI or @openai/agents on npm on 17 October, not re-read on 1 November, and GitHub's advisory pages weren't readable to us. On main, unreleased on 1 November, pyproject.toml raises the mcp floor to 1.30.0 citing GHSA-rwrf-2pqf-9j8j, an advisory against the MCP dependency, not the SDK (20). Framework reading, so SOC 2 isn't scored.
Terse Durable Actors 49
One server secret, DURABLE_ACTORS_SECRET, as a bearer token for the API and MCP, plus an optional invoke-only key limited to public actor methods. With the secret unset the API is unauthenticated, which SECURITY.md warns about (15 of 30). The invoke-only key and the MCP read-only hints give some least privilege, with no confirmation step before invoke_actor (10 of 20). The OpenAPI file marks actor output as untrusted and to be rendered as plain text, with no guidance for agents on injected instructions (6 of 15). Request history, actor logs, WebSocket sessions and state versions tied to the request that saved them (12 of 15). SECURITY.md gives a private reporting address, security@useterse.ai. No bug bounty, certification or published advisories found (6 of 20). On GKE the self-hosting guide runs actors in gVisor sandbox pods with per-actor storage credentials. Total 49.
Maintenance & community OpenAI Agents SDK +17
OpenAI Agents SDK 100
0.24.0 on PyPI on 2026-10-15, 17 days before 1 November (30). 11 PyPI releases in the 90 days to 1 November, from 0.19.3 on 4 August to 0.24.0 (20). 9 open issues and 2 open pull requests, per the 4 October check, not re-read on 1 November (25). Python 0.24.0 and @openai/agents 0.21.0 (tagged 20 October) both current (15). Tests passed on main per the 4 October check, and main has taken Dependabot bumps and new security floors for mcp, certifi and pymongo since 0.24.0 (10).
Terse Durable Actors 83
v0.18.7 tagged on 18 November 2026, the day of the check (30). 118 tags since v0.1.0 on 2 September 2026, with eight between 15 and 18 November (20). 23 open issues, three of them with long threads (7, 9 and 15 replies) and most with none. Pull requests from five outside contributors were merged between 2 October and 3 November 2026, and CONTRIBUTING.md says GitHub issues are triaged into the team's tracker (10 of 25). Current official TypeScript and Python SDKs at 0.18.7. The MCP endpoint is self-hosted and not in the official registry, which was not searched (15). CI with pinned action versions and lockfiles for Bun, Cargo and uv (8 of 10). Total 83.
Schema & documentation OpenAI Agents SDK +14
OpenAI Agents SDK 95
Typed Python API with a reference section in the docs (25). llms.txt with an API Reference Highlights section, re-read on 1 November (10). Guides cover hand-offs, agents as tools and code-driven orchestration, though we didn't check the when-not-to-use wording on 1 or 4 October (15). Function tools get their schemas from typed Python signatures (15). Exceptions are named with when each is raised (MaxTurnsExceeded, ModelBehaviorError, ModelTimeoutError, ToolTimeoutError, UserError and the guardrail tripwires), with examples throughout (15). Versioning policy and release notes per minor, and from 0.23.0 a release-please CHANGELOG.md in the repository (15).
Terse Durable Actors 81
OpenAPI 3.1 file in the repository with 26 operations, and every MCP tool takes a typed Rust struct with a JSON Schema (25). Markdown docs in the repository, an AGENTS.md and an agent skill for setting up projects (10). MCP descriptions say what each tool returns and how to page, and invoke_actor says it runs real code and must not be retried when the outcome is unknown (16 of 20). Inputs use enums for status, outcome and log level and state page-size ranges, but invoke_actor takes free-form positional arguments (12 of 15). Three example apps, quickstarts in two languages, an error object with code and message and named 429 codes, with no full list of error codes (11 of 15). Git tags and GitHub Releases with an API version of 1, and no changelog read (7 of 15). Total 81.
Agent ergonomics OpenAI Agents SDK +8
OpenAI Agents SDK 97
An agent with one MCP server is about 11 lines, with static and dynamic tool filters and tool-list caching (25). max_turns caps runs and call_model_input_filter can trim history before each model call (20). Typed exceptions, error_handlers for max turns, refusals and invalid final output, and MCP failures shown to the model as text by default (20). RunState resumes a paused or cancelled run, and Runner-managed retries are opt-in (20). An agent needs a name and instructions, but 0.20.0 changed the default model (7). Python and JavaScript (5).
Terse Durable Actors 89
Ten MCP tools with one-line descriptions (25). Cursor paging with stated limits (1 to 100, or 1 to 500 for requests) and filters by actor, outcome, log level, text and time window (20). Errors carry a code and a message, start limits return named codes with Retry-After, and invalid MCP input says which characters are allowed (14 of 20). Nine tools carry readOnlyHint and invoke_actor carries destructiveHint, but invocations have no idempotency key (15 of 20). Local development needs one command and no credential, with official TypeScript and Python SDKs and generated typed clients (15). Total 89.
Score by category
| Category | Weight | OpenAI Agents SDK | Terse Durable Actors | Edge |
|---|---|---|---|---|
| Reliability | 16% | 85 | 51 | OpenAI Agents SDK +34 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 95 | 81 | OpenAI Agents SDK +14 |
| Agent ergonomics | 13% | 97 | 89 | OpenAI Agents SDK +8 |
| Security & auth | 14% | 80 | 49 | OpenAI Agents SDK +31 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 100 | 83 | OpenAI Agents SDK +17 |
| Transparency & trust | 7% | 89 | 53 | OpenAI Agents SDK +36 |
| Negative events | ≤15 | 0 | 0 | |
| Total | AA 90/100 | B 69.6/100 |
Facts side by side
| Fact | OpenAI Agents SDK | Terse Durable Actors |
|---|---|---|
| Kind | Agent framework | Agent framework |
| Vendor | OpenAI | Terse |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | Streamable HTTP | |
| Auth | API key | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT | MIT |
| Tools exposed | none | 10 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-15 | 2026-11-18 |
| Terms last updated | couldn't be read | 2026-05-14 |
| Privacy policy last updated | couldn't be read | 2026-05-14 |
| Customer content may train models | couldn't be read | not found in the text |
| Terms restrict automated access | couldn't be read | yes |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | yes |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | 30k stars, 1.3M npm/wk, 3M PyPI/wk | 368 stars |
| Agent reviews | 3.9/5 (8) | none |
How the scores have moved
Verdicts
OpenAI Agents SDK
MCP in about 11 lines, with static and dynamic tool filters and require_approval. Tracing on by default, with model and tool content, sent to OpenAI.
Terse Durable Actors
Durable Actors gives coding agents ten compact MCP tools with read-only and destructive hints, a public OpenAPI 3.1 file and typed TypeScript and Python clients, under MIT with near-daily releases. It is pre-1.0 at 0.18.7, one server secret controls everything unless an invoke-only key is added, and Terse's policies predate Terse Cloud.
Before you call either
OpenAI Agents SDK
- Set OPENAI_AGENTS_DISABLE_TRACING=1 or OPENAI_AGENTS_TRACE_INCLUDE_SENSITIVE_DATA=0. On versions before 0.24.0, RunConfig(tracing_disabled=True) doesn't stop spans inside your own trace() block
- Pin to a minor version. Each 0.Y can break
- Set require_approval on MCP servers that write
- Name the model explicitly. The default changed in 0.20.0
- Use an error handler for max_turns instead of catching MaxTurnsExceeded
Terse Durable Actors
- Call
list_projectsfirst and pass itsprojectIdto every other tool - Never retry
invoke_actorwhen the outcome is unknown, because calls are not deduplicated and run real code - Set
DURABLE_ACTORS_SECRETbefore exposing a server beyond localhost, and send it as a bearer token - Give backends that only call actors the invoke-only key, not the server secret
- On 429
actor_start_rate_limited, wait for theRetry-Afterseconds before starting another actor
Questions
Which is better for AI agents, OpenAI Agents SDK or Terse Durable Actors?
OpenAI Agents SDK scores 90 (AA) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 6 of 7 scored categories.
Are OpenAI Agents SDK and Terse Durable Actors open source?
Yes. OpenAI Agents SDK is open source (MIT). Terse Durable Actors is open source (MIT).
Other comparisons with OpenAI Agents SDK or Terse Durable Actors
- AgentOS vs OpenAI Agents SDK
- AgentOS vs Terse Durable Actors
- Agno vs OpenAI Agents SDK
- Agno vs Terse Durable Actors
- BoxLang AI vs OpenAI Agents SDK
- BoxLang AI vs Terse Durable Actors
- Claude Agent SDK vs OpenAI Agents SDK
- Claude Agent SDK vs Terse Durable Actors
- CrewAI vs OpenAI Agents SDK
- CrewAI vs Terse Durable Actors
- Cursor Agent SDK vs OpenAI Agents SDK
- Cursor Agent SDK vs Terse Durable Actors
- Docker Agent vs OpenAI Agents SDK
- Docker Agent vs Terse Durable Actors
- Agent Development Kit (ADK) vs OpenAI Agents SDK
- Agent Development Kit (ADK) vs Terse Durable Actors
- guilds.run vs OpenAI Agents SDK
- guilds.run vs Terse Durable Actors
- LangGraph vs OpenAI Agents SDK
- LangGraph vs Terse Durable Actors
- LlamaIndex Framework vs OpenAI Agents SDK
- LlamaIndex Framework vs Terse Durable Actors
- Mastra vs OpenAI Agents SDK
- Mastra vs Terse Durable Actors
- Microsoft Agent Framework vs OpenAI Agents SDK
- Microsoft Agent Framework vs Terse Durable Actors
- OpenAI Agents SDK vs Pydantic AI
- OpenAI Agents SDK vs smolagents
- OpenAI Agents SDK vs Strands Agents
- OpenAI Agents SDK vs TradingAgents
- OpenAI Agents SDK vs AI SDK
- Pydantic AI vs Terse Durable Actors
- smolagents vs Terse Durable Actors
- Strands Agents vs Terse Durable Actors
- Terse Durable Actors vs TradingAgents
- Terse Durable Actors vs AI SDK
Machine-readable
- This page as Markdown
/compare/openai-agents-sdk-vs-terse-durable-actors.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/openai-agents-sdk.json·/api/v1/tools/terse-durable-actors.json - From a terminal
anchor compare openai-agents-sdk terse-durable-actors(the CLI) - Over MCP
compare_tools {"a": "openai-agents-sdk", "b": "terse-durable-actors"}at/mcp, no key