# Cursor Agent SDK vs AI SDK (slim)

> AI SDK scores 89.8 (AA) to Cursor Agent SDK's 63.7 (B) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-vercel-ai-sdk.md (~5,050 tokens) · this version ~3,030 tokens · JSON https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-vercel-ai-sdk.json · canonical https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-vercel-ai-sdk
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

AI SDK scores 89.8 (AA) on agent readiness against Cursor Agent SDK's 63.7 (B), and leads in every scored category. Both do agent frameworks.

- Cursor Agent SDK: B 63.7, rank #501 of 1486 · https://www.anchorterminal.com/tools/cursor-agent-sdk.min.md
- AI SDK: AA 89.8, rank #1 of 1486 · https://www.anchorterminal.com/tools/vercel-ai-sdk.min.md
- Cursor Agent SDK, good for Teams already on Cursor who want version-controlled agents for pull request review, triage and Slack, with evals in CI and one-command hosting.
- AI SDK, good 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 45; Schema & documentation, 100 against 82; Agent ergonomics, 95 against 80; Security & auth, 90 against 68; Payments & pricing, 60 against 30; Maintenance & community, 97 against 74; Transparency & trust, 89 against 71. Also Agent-ready, a grade of BB or better; Open source.

| Category | Cursor Agent SDK | AI SDK |
| --- | --- | --- |
| Reliability (16%) | 45 | 93 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 82 | 100 |
| Agent ergonomics (13%) | 80 | 95 |
| Security & auth (14%) | 68 | 90 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 74 | 97 |
| Transparency & trust (7%) | 71 | 89 |

| Fact (where they differ) | Cursor Agent SDK | AI SDK |
| --- | --- | --- |
| Vendor | Cursor | Vercel Inc. |
| Auth | OAuth or key | API key |
| Pricing | Your plan | Free |
| Licence | Proprietary. The package's LICENSE.md reads "© Anysphere Inc. All rights reserved", with use subject to Cursor's Terms of Service (updated 3 September 2026). No source repository is published | Apache-2.0 |
| Last release | 2026-10-25 | 2026-11-05 |
| Terms last updated | 2026-09-03 | 2026-06-01 |
| Privacy policy last updated | 2026-09-29 | 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 | yes | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Popularity | none | 28k stars, 44.9M npm/wk |

Why the edge:
- Reliability, AI SDK +48: Cursor Agent SDK 45 (Local-package reading, since the owner runs the framework, with Cursor's hosting as an option. Official npm package with Node 22.13 or newer stated in engines and in the docs, which also say never Bun (20). Closed source, so no public CI or test suite (0). No public issue tracker. github.com/cursor/cursor holds a README and SECURITY.md, and forum.cursor.com has no Agent SDK tag, so there's nothing to count open crashes against. The troubleshooting page lists known failures with fixes (5). A dated changelog of two entries, 0.2.29 and 0.3.0, both 23 October 2026, and 0.3.0 calls out the removed `persistent` option, but the 27 earlier @cursor/bdk versions and 123 @cursor/july versions have no notes, and one build ships under three package names (5). Version 0.3.0, but the changelog post of 20 October says generally available and the docs changelog labels 0.3.0 the GA release, which we read as declared stable (15). 20+0+5+5+15 = 45.); 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.)
- Payments & pricing, AI SDK +30: Cursor Agent SDK 30 (Framework reading of the published rubric. No payment protocol (0). Per-million-token prices for Cursor models, including the default Grok 4.5 with Fast, and plan prices are public, but no price for managed hosting and no statement of which plans cover the Agent SDK were found (15). The package is free and the Free plan needs no card, but its usage is only described as limited agent requests (15). A person signs in through a browser or creates an API key in the dashboard before a model turn runs (0). 0+15+15+0 = 30.); AI SDK 60 (No payment protocol (0). Scored on the AI Gateway, the paid option, which charges providers' list prices with no markup and lists per-model rates and add-on prices without a login (20). The Apache 2.0 package installs with no card (20) and no account, and provider packages run any model, including local ones (20).)
- Maintenance & community, AI SDK +23: Cursor Agent SDK 74 (0.3.0 on npm on 25 October 2026, per the 27 October check (npm not re-read on 2 November), and the docs changelog still ends at 0.3.0 of 23 October (30). Five @grok/agent-sdk versions from 22 to 25 October and 29 @cursor/bdk versions since 22 September, per the 27 October check (20). Closed product. A public changelog with two entries and a forum with no Agent SDK tag, so we couldn't see replies to SDK reports (8). The npm package is current and official, TypeScript only (12). Dependencies are current releases, but there's no public CI and the same build goes out under three names with a postinstall script (4). 30+20+8+12+4 = 74.); 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.)
- Security & auth, AI SDK +22: Cursor Agent SDK 68 (Framework reading. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt injection, 15 for audit and 20 for the security programme. Every model turn goes through Cursor's backend with a Cursor credential, even on a self-hosted server, and the data-use page says Cursor may store and train on prompts and code with Privacy Mode off. Managed hosting stores the repository and agent data whatever the Privacy Mode setting. OpenTelemetry export is off until an endpoint is set, with prompt text and tool payloads behind separate flags, and the npm update check has a documented switch. Install copies skills into ~/.cursor/skills (18). `needsApproval` parks a tool call for a person, dry runs stub writes and the harness tools take an allowlist, but `local.sandbox` is off by default, so shell commands auto-approve with the host's environment and file tools reach any path the process can. Hosted deployments enforce an egress allowlist (12). The docs tell you to turn the sandbox on for webhook payloads, diffs and chat, document HMAC and shared-secret auth on webhook routes, and warn that anyone who can talk to the agent can drive Cursor account connectors. The scaffolded memory journal shares turns across sessions, with an instruction to treat it as untrusted (10). Sessions keep every message and tool call, hooks can mirror them for audit, and `ctx.approvedBy` records the approver (14). security.txt and SECURITY.md with a disclosure address and Cursor's GitHub advisories, no bug bounty found, and no advisory for the three package names in OSV on 2 November (14). SOC 2 and ISO 27001 aren't scored on the framework reading. 18+12+10+14+14 = 68.); 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.)
- Schema & documentation, AI SDK +18: Cursor Agent SDK 82 (Framework reading. Typed TypeScript declarations ship in the package, tools take Zod or JSON Schema, `agent-sdk help --json` describes every command's flags and exit codes, and `GET /v1/info` and `GET /v1/tools/:name` return the discovered surface and each tool's schemas. No OpenAPI document for the HTTP routes (20). cursor.com/llms.txt lists every Agent SDK page with a Markdown twin, and the package ships the docs and an llms.txt (10). The overview has a table of when to use the Agent SDK, Automations or Grok Bot, and the hooks page has a table of what to use instead of a hook for each job (18). Typed config, `effect` as an enum or predicate, `timeArgs` checked against the input schema, and slug patterns stated (13). Examples on every page, with error tables for direct tool calls, HTTP 401, 403 and 409, the limit error's JSON and seven exit codes (15). A dated changelog, but only two entries, both from 23 October 2026 (6). 20+10+18+13+15+6 = 82.); 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).)
- Transparency & trust, AI SDK +18: Cursor Agent SDK 71 (Closed source. LICENSE.md reads All rights reserved, with use under Cursor's Terms of Service of 3 September 2026 (15). The data-use page says Privacy Mode keeps Customer Data out of training with zero-retention agreements at model providers, and that with it off Cursor may store and train on code and prompts. The deployment page says managed hosting stores the repository and agent data the same way under Privacy Mode and refuses Privacy Mode (Legacy). No retention periods are stated, and subprocessors are on a trust portal (14). No deprecation policy. The early-alpha migration guide, the `persistent` removal and the semantic-search removal are documented with error messages but only the changelog entry carries a date (6). OpenTelemetry and the update check are documented with switches. What the Cursor backend logs from turns is covered only by the data-use page (14). 15+14+6+14 = 49.); 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).)