Head to head · Agent durable · October 2026 research run
Terse Durable Actors vs AI SDK
AI SDK scores 93.6 (AA) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 6 of 7 scored categories. Both do agent durable.
Best agent frameworks and SDKs · All 190 frameworks comparisons
Which one, for what
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
AI SDK AA
Best for TypeScript teams building agents and chat UIs who want one API across many providers and a short path to MCP.
Ahead on
- Reliability, 93 against 51
- Schema & documentation, 100 against 81
- Agent ergonomics, 95 against 89
- Security & auth, 90 against 49
- Maintenance & community, 97 against 83
- Transparency & trust, 89 against 53
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
TypeScript only, and ai 7.x needs Node 22 or newer
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.
Reliability AI SDK +42
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.
AI SDK 93
Official npm packages, with ai 7.x requiring Node 22 or newer (20). A public CI workflow with lint, type checks, unit tests, Node-version tests, MCP tests on Windows and e2e tests runs on every push to main, and the newest completed CI runs on main passed on 6 November (25). 1,517 open issues and pull requests on 6 November from GitHub's API, with 1,059 issues opened in the 90 days to 3 November; 47 of the 50 newest had a comment and 32 were closed (18). A written versioning page with breaking changes only in majors, experimental_ prefixes for unstable APIs and a migration guide per major (15). 7.0.163 (15). 20+25+18+15+15 = 93, up from 73 on 6 October, when GitHub couldn't be read.
Security & auth AI SDK +41
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.
AI SDK 90
No telemetry until an OpenTelemetry integration is registered. String model IDs route to Vercel's AI Gateway by default, which is documented and needs a Vercel key, so it isn't silent (25). Per-tool approval, HMAC-signed approvals against forged client history, and Open Policy Agent rules in @ai-sdk/policy-opa, though sandboxes are experimental (20). ToolLoopAgent rejects system messages in prompts by default as an injection risk, URL fetches are checked against private addresses, and MCP HTTP transport refuses redirects by default, but there's no guardrail primitive (10). OpenTelemetry spans for every model and tool call to any backend, opt-in (15). HackerOne programme, a valid security.txt, SECURITY.md and two low-severity advisories published with fixed versions (20). Framework reading, so SOC 2 isn't scored.
Transparency & trust AI SDK +36
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.
AI SDK 89
Apache 2.0 (30). The library stores nothing. The AI Gateway's ZDR page says it doesn't retain prompts or outputs and per-request ZDR is available on Pro and Enterprise, and Vercel's privacy notice is dated 1 June 2026, but we didn't read a DPA or subprocessor list (22). Deprecated APIs are removed only at majors with a migration guide, and 6.x and 5.x keep getting releases, without a written support window (14). Telemetry is opt-in and documented, with switches for inputs and outputs (20).
Schema & documentation AI SDK +19
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.
AI SDK 100
Typed TypeScript API with a reference section for every function (25). llms.txt and a Markdown copy of each page (10). The docs say when to use each piece, such as a table of WorkflowAgent against ToolLoopAgent, a when-to-use section for subagents and harnesses, and HTTP over stdio for MCP in production (20). Tools take Zod or JSON Schema inputs (15). 38 error types documented in the reference, with error-handling guides and examples throughout (15). Versioning page and a changesets CHANGELOG per package (15).
Maintenance & community AI SDK +14
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.
AI SDK 97
7.0.163 on 2026-11-05 (30). 226 stable npm releases of ai across the 7.x, 6.x and 5.x lines in the 90 days to 6 November, 70 of them since 6 October (20). 47 of the 50 newest issues commented and 32 closed, with triage automation and backport workflows (22). ai and the provider packages are current, and 6.x and 5.x still get patches (15). Dependabot configured and CI passing on main (10). 30+20+22+15+10 = 97.
Agent ergonomics AI SDK +6
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.
AI SDK 95
An MCP client in a few lines with createMCPClient and client.tools(), and tool search with deferLoading keeps unused tool definitions out of the prompt (25). stopWhen with a default of 20 steps, and prepareStep to trim messages, switch models or limit active tools per step (20). 38 typed errors with isInstance guards, and MCP results with isError go back to the model (20). maxRetries on model calls, opt-in retries for transient MCP failures only, and WorkflowAgent for durable steps with automatic retries (20). Few required parameters, but TypeScript only, and a string model ID needs an AI Gateway key unless a default provider is set (10).
Score by category
| Category | Weight | Terse Durable Actors | AI SDK | Edge |
|---|---|---|---|---|
| Reliability | 16% | 51 | 93 | AI SDK +42 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 81 | 100 | AI SDK +19 |
| Agent ergonomics | 13% | 89 | 95 | AI SDK +6 |
| Security & auth | 14% | 49 | 90 | AI SDK +41 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 83 | 97 | AI SDK +14 |
| Transparency & trust | 7% | 53 | 89 | AI SDK +36 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 69.6/100 | AA 93.6/100 |
Facts side by side
| Fact | Terse Durable Actors | AI SDK |
|---|---|---|
| Kind | Agent framework | Agent framework |
| Vendor | Terse | Vercel |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | Streamable HTTP | |
| Auth | API key | API key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Tools exposed | 10 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-18 | 2026-11-05 |
| Terms last updated | 2026-05-14 | 2026-06-01 |
| Privacy policy last updated | 2026-05-14 | 2026-06-01 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 368 stars | 28k stars, 44.9M npm/wk |
How the scores have moved
Verdicts
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.
AI SDK
A TypeScript agent toolkit with ToolLoopAgent, a built-in MCP client, per-tool approvals that can be HMAC-signed, opt-in OpenTelemetry and durable runs through WorkflowAgent. It ships three major versions in 14 months (5.0, 6.0, 7.0), each with a migration guide, and plain string model IDs route through Vercel's AI Gateway unless another provider is set.
Before you call either
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
AI SDK
- Pass a provider instance such as openai('model') if traffic shouldn't go through Vercel's AI Gateway
- Set toolApproval on tools that write, and experimental_toolApprovalSecret when approvals come back from a browser
- Raise or replace the default stop condition of 20 steps with stopWhen
- Close the MCP client after the run, and use HTTP transport outside local development
- Set recordInputs and recordOutputs to false when spans would carry secrets
Questions
Which is better for AI agents, Terse Durable Actors or AI SDK?
AI SDK scores 93.6 (AA) on agent readiness against Terse Durable Actors's 69.6 (B), and leads in 6 of 7 scored categories.
Are Terse Durable Actors and AI SDK open source?
Yes. Terse Durable Actors is open source (MIT). AI SDK is open source (Apache-2.0).
Other comparisons with Terse Durable Actors or AI SDK
- AgentOS vs Terse Durable Actors
- AgentOS vs AI SDK
- Agno vs Terse Durable Actors
- Agno vs AI SDK
- BoxLang AI vs Terse Durable Actors
- BoxLang AI vs AI SDK
- Claude Agent SDK vs Terse Durable Actors
- Claude Agent SDK vs AI SDK
- CrewAI vs Terse Durable Actors
- CrewAI vs AI SDK
- Cursor Agent SDK vs Terse Durable Actors
- Cursor Agent SDK vs AI SDK
- Docker Agent vs Terse Durable Actors
- Docker Agent vs AI SDK
- Agent Development Kit (ADK) vs Terse Durable Actors
- Agent Development Kit (ADK) vs AI SDK
- guilds.run vs Terse Durable Actors
- guilds.run vs AI SDK
- LangGraph vs Terse Durable Actors
- LangGraph vs AI SDK
- LlamaIndex Framework vs Terse Durable Actors
- LlamaIndex Framework vs AI SDK
- Mastra vs Terse Durable Actors
- Mastra vs AI SDK
- Microsoft Agent Framework vs Terse Durable Actors
- Microsoft Agent Framework vs AI SDK
- OpenAI Agents SDK vs Terse Durable Actors
- OpenAI Agents SDK vs AI SDK
- Pydantic AI vs Terse Durable Actors
- Pydantic AI vs AI SDK
- smolagents vs Terse Durable Actors
- smolagents vs AI SDK
- Strands Agents vs Terse Durable Actors
- Strands Agents vs AI SDK
- TradingAgents vs AI SDK
- Terse Durable Actors vs TradingAgents
Machine-readable
- This page as Markdown
/compare/terse-durable-actors-vs-vercel-ai-sdk.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/terse-durable-actors.json·/api/v1/tools/vercel-ai-sdk.json - From a terminal
anchor compare terse-durable-actors vercel-ai-sdk(the CLI) - Over MCP
compare_tools {"a": "terse-durable-actors", "b": "vercel-ai-sdk"}at/mcp, no key