# AI SDK > Open-source TypeScript toolkit from Vercel for building AI applications and agents, with a provider-agnostic API, a ToolLoopAgent, an MCP client and UI hooks for React, Vue, Svelte and Angular. - Canonical: https://www.anchorterminal.com/tools/vercel-ai-sdk - Pricing: https://www.anchorterminal.com/tools/vercel-ai-sdk#pricing - Reviews: https://www.anchorterminal.com/tools/vercel-ai-sdk#reviews - Markdown: https://www.anchorterminal.com/tools/vercel-ai-sdk.md (~7,250 tokens) - Slim: https://www.anchorterminal.com/tools/vercel-ai-sdk.min.md (~1,330 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/vercel-ai-sdk.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT vercel-ai-sdk.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade AA · 89.8/100 · rank #1 of 1486 · #1 in Agent frameworks & SDKs · agent-ready · confidence medium** ## Assessment 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. ## Facts | Field | Value | | --- | --- | | Vendor | Vercel Inc. (https://vercel.com) | | Kind | Agent framework | | Category | Agent frameworks & SDKs (https://www.anchorterminal.com/categories/frameworks) | | Auth | API key · The SDK has no account of its own. Each provider package takes that provider's key. Plain string model IDs resolve through Vercel's AI Gateway by default, which needs AI_GATEWAY_API_KEY or a Vercel OIDC token. | | Pricing | Free (Free · OSS) · Free and open source. You pay for model calls. The optional AI Gateway charges providers' list prices with no markup, from prepaid credits, with a free monthly credit on a subset of models (https://vercel.com/docs/ai-gateway/pricing, checked 2026-11-06). | | x402 | No · No x402, MPP or L402 in the AI SDK docs, the vercel/ai repository's packages or the AI Gateway pricing page. The tools registry in the repository lists a third-party x402 marketplace tool (checked 2026-10-06). | | Licence | Apache-2.0 | | Packages | npm: `ai`; npm: `@ai-sdk/mcp`; npm: `@ai-sdk/workflow` | | Source | https://github.com/vercel/ai | | Docs | https://ai-sdk.dev/docs | | llms.txt | https://ai-sdk.dev/llms.txt | | Last release | 2026-11-05 | | GitHub stars | 27,781 (as of 2026-11-06) | | npm downloads / week | 44,868,298 | | Languages | TypeScript and JavaScript, Node 22 or newer for `ai` 7.x | | Models | Provider packages for OpenAI, Anthropic, Google, Amazon Bedrock and others, or any model through the AI Gateway | | MCP client | @ai-sdk/mcp 2.0.91, HTTP (recommended), SSE and stdio (experimental) transports, OAuth, opt-in retries for tools/call, stateless MCP 2026-07-28 | | Multi-agent | Subagents run as tools of a parent agent | | Durable state | WorkflowAgent in @ai-sdk/workflow, each tool call a durable workflow step | | Human approval | toolApproval per tool or per request, HMAC-signed approvals, Open Policy Agent rules in @ai-sdk/policy-opa | | Guardrails | None built in. Middleware and prepareStep can filter | | Tracing | OpenTelemetry through @ai-sdk/otel | | Telemetry | None until an integration is registered | | Releases in 90 days | 226 stable releases of `ai` on npm to 6 November 2026 | | Capabilities | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | | Tags | framework, typescript, open-source, llms-txt, mcp, otel | | JSON | https://www.anchorterminal.com/api/v1/tools/vercel-ai-sdk.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 93 | 18.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 100 | 16.2 | | Agent ergonomics | 13% | 16.2 | 95 | 15.4 | | Security & auth | 14% | 17.5 | 90 | 15.8 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 97 | 8.5 | | Transparency & trust (editorial 86, provenance 91) | 7% | 8.8 | 89 | 7.8 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **89.8 → AA** | ### Why each score - Reliability 93 (checked 2026-11-06): 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. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 100 (checked 2026-11-06): 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). - Agent ergonomics 95 (checked 2026-11-06): 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). - Security & auth 90 (checked 2026-11-06): 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. - Payments & pricing 60 (checked 2026-11-06): 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). - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 97 (checked 2026-11-06): 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. - Transparency & trust 89 (checked 2026-11-06): 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). Fix list, everything this grade says the listing lacks, the biggest gain first (11 items). What it covers is at https://www.anchorterminal.com/fixes/vercel-ai-sdk.md (JSON https://www.anchorterminal.com/fixes/vercel-ai-sdk.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "vercel-ai-sdk", "plan": "read"}`, free while the beta runs ### What we couldn't check - Changed since 6 October 2026 (rechecked 6 November). `ai` went from 7.0.128 to 7.0.163 (5 November) and @ai-sdk/mcp from 2.0.67 to 2.0.91, with 6.x and 5.x still patched; no new advisory on OSV for `ai` or @ai-sdk packages; telemetry still opt-in through @ai-sdk/otel; versioning page, licence, AI Gateway pricing and Vercel's security.txt unchanged. GitHub's API answered this time, so CI on main and issue activity were read first-hand (reliability 73 to 93, maintenance 84 to 97); other scores unchanged - We didn't read Vercel's DPA or subprocessor list for the AI Gateway - The AI Gateway pricing page read on 6 November says free credits cover a subset of models with lower rate limits, without stating the monthly amount ### Sources - npm registry document for ai (versions and dates): (seen 2026-11-06) - npm weekly downloads: (seen 2026-11-06) - repository clone (docs, CI workflow, SECURITY.md, CHANGELOG): (seen 2026-10-06) - versioning: (seen 2026-11-06) - MCP tools: (seen 2026-10-06) - telemetry: (seen 2026-11-06) - tool approvals: (seen 2026-10-06) - WorkflowAgent: (seen 2026-10-06) - llms.txt: (seen 2026-11-06) - AI Gateway pricing: (seen 2026-11-06) - AI Gateway zero data retention: (seen 2026-10-06) - security.txt: (seen 2026-11-06) - privacy notice: (seen 2026-10-06) - OSV advisories for @ai-sdk/provider-utils: (seen 2026-11-06) - npm registry document for @ai-sdk/mcp: (seen 2026-11-06) - GitHub API, repository, issues and Actions runs on main: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/vercel-ai-sdk/history.json - 2026-11-06: graded 89.8 AA (methodology 0.7) ## Who's behind it (provenance 91/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Vercel Inc. | 20/20 | | Domain age | ai-sdk.dev, registered 2024-09-26 (2 years) | 7/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | read, states 7 of the 7 things a reader expects | 10/10 | | Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 | | Status page | www.vercel-status.com | 10/10 | | Changelog | published | 10/10 | | security.txt | valid | 10/10 | | People named | 2 named with their role, 1 with a public profile | 10/10 | | Support route | a support address, help pages, a community | 5/5 | The privacy notice (effective 1 June 2026) names Vercel Inc. vercel.com/.well-known/security.txt points to HackerOne and responsible.disclosure@vercel.com and expires 2027-09-28. RDAP gives ai-sdk.dev a registration date of 2024-09-26 and vercel.com 1999-10-04. The status page covers Vercel's hosted services, including the AI Gateway, not the library. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://vercel.com/legal/terms), read 2026-10-08, dated 2026-06-01, states 7 of the 7 things a reader expects. - To know. Says it may use customer content to train or improve models, and gives an opt-out. "In addition, if you are on a Hobby plan or trial Pro plan, you agree that we may use Your Content to train our artificial intelligence ("AI") and machine learning models, and we may share Your Content with third parties for the purpose of developing and improving their products, including training and improving their…" - To know. Says access can be ended without notice or for any reason. "We may shut down and terminate projects or deployments using the Hobby plan without notice for any reason or no reason." - To know. Requires arbitration or waives class actions. "You and Vercel agree that any Claim will be settled by final and binding arbitration, using the English language, administered by JAMS under its Streamlined Arbitration Rules and Procedures (the "JAMS Rules")." - Gives the date it was last updated. Last updated 2026-06-01. - Names the governing law or courts. The law of the State of California. - Says how changes to the terms are announced. Says it gives notice of a change. - Also in the text (2026-10-08). A customer that lets its own or a third party's AI tools or agents access the service agrees to be legally bound by the actions those tools take on its behalf. "you authorize and agree to be legally bound by the actions taken on your behalf by those Third Party Tools" - Also in the text (2026-10-08). During the agreement Vercel may use the customer's trademarks, trade names and logos in its marketing materials and websites and name it as a customer. "During the term of this Agreement, you grant Vercel a non-exclusive, royalty-free, fully-paid up license to use and reproduce your trademarks, trade names and logos in Vercel's marketing materials and website(s) and to indicate that you are a Vercel customer." - Also in the text (2026-10-08). The licence over customer content is sublicensable and transferable and covers improving the services and developing new products and services. "a worldwide, non-exclusive, royalty-free, fully paid, sublicensable and transferable license to use, copy, modify, adapt, reproduce, distribute, display, publish, store, perform, and create derivatives of Your Content to provide and improve the Services, develop new products and services" **Privacy policy** (https://vercel.com/legal/privacy-policy), read 2026-10-08, dated 2026-06-01, states 7 of the 8 things a reader expects. - To know. Says it may use customer content to train or improve models, and gives an opt-out. "Services, such as when we use your information to train the AI models" - To know. Says it sells personal data or shares it for advertising. "We engage with several partners, such as third-party advertising networks, integration service partners, event sponsors, and resellers. We may share information with them to provide and support our Services, and to conduct our Advertising and Marketing Activities." - Gives the date it was last updated. Last updated 2026-06-01. - Not found in the text. Says how long data is kept. - Gives a privacy contact. privacy@vercel.com. - Says where data is transferred or stored. Relies on standard contractual clauses. - Also in the text (2026-10-08). For Hobby and Pro plans, subject to team settings, Vercel may disclose de-identified information to AI business partners for training and improving their models. "we may disclose de-identified information (including de-identified AI Product Information) to AI business partners for their product improvement and development, including training and improving AI and machine learning models" ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Guillermo Rauch, Founder and CEO, Vercel. X: https://x.com/rauchg - Malte Ubl, Chief Technology Officer, Vercel - Note: Vercel's about page, read on 28 October 2026, lists its individual investors but no leaders. Its press page calls Guillermo Rauch Vercel's CEO and Malte Ubl its CTO, and blog bylines give Rauch as CEO and Founder, Vercel (Series F post, 30 September 2025) and Ubl as CTO, Vercel. Wikipedia names Rauch as the sole founder of the company, which began as ZEIT in 2015. Product people named on single listings are left as they are. Copied from the Vercel AI Gateway listing (checked 28 October 2026) for the AI SDK on 6 November 2026, without the AI Gateway product manager. No AI SDK maintainer was added, since none was confirmed from a first-hand page in this pass. On 6 November 2026 SiliconANGLE's Series F report added BlackRock, StepStone and Khosla Ventures as new investors in that round. The total raised is left out: the last figure Vercel states is $313M, in its Series D post of November 2021, and no first-hand or reputable source read states a total after the Series E and F rounds (only trackers the rules exclude do). No round after the Series F was found in Vercel's sitemap. - Vercel Inc.: LinkedIn https://www.linkedin.com/company/vercel X https://x.com/vercel ### Ownership and investors - Valuation: $9.3B as announced (the source doesn't say pre- or post-money), Series F, September 2025 (source https://vercel.com/blog/series-f) - Backed by: Accel, GIC, CRV, GV, Bedrock, Notable Capital, Greenoaks, Geodesic Capital, 8VC, Flex Capital, Latacora, Salesforce, Tiger Global, SV Angel, Caffeinated Capital, Resolute Capital Partners, S28 Capital, TrueBridge Capital Partners, Nat Friedman, Jordan Walke, Naval Ravikant, Jessie Frazelle, Ilya Sukhar, David Cramer, Anthony Casalena, Soleio Cuervo, Matias Woloski, Michael Stoppelman, Pete Hunt, Brendan Eich, Sahil Lavingia, Rasmus Andersson, Benjamin De Cock, Alexandr Wang, Karri Saarinen, BlackRock, StepStone Group, Khosla Ventures ### Getting support - Support email: billing@vercel.com - Help: https://vercel.com/help - Help: https://community.vercel.com/ - Community (Community forum): https://community.vercel.com/ - Sources: https://www.linkedin.com/in/jerilynzheng/details/experience/, https://vercel.com/blog/zdr-on-ai-gateway, https://www.linkedin.com/in/jerilynzheng, https://x.com/jerilynzheng, https://rauchg.com/about, https://vercel.com/, https://vercel.com/ai-gateway, https://vercel.com/help, https://vercel.com/kb/guide/how-to-get-vercel-support, https://vercel.com/about ## Live (updated 2026-11-07 18:22 UTC) - Vendor status page: no problems reported, All Systems Operational - github `vercel/ai` @ai-sdk/zai@2.0.19, released 2026-11-06 - npm `@ai-sdk/mcp` 2.0.92 - npm `@ai-sdk/workflow` 2.0.96 - npm `ai` 7.0.164 - security.txt: none - Watching changelog - Always current: https://www.anchorterminal.com/api/v1/live/vercel-ai-sdk.json ## Probe metrics A library has no endpoint to probe. Reliability is assessed from its tests, release history and issue tracker; performance waits for the task suite run through it. See https://www.anchorterminal.com/benchmark/#kinds ## Strengths - Apache 2.0, with 246 npm releases of `ai` in the 90 days to 6 October 2026 - MCP client in @ai-sdk/mcp with HTTP, SSE and stdio transports, OAuth and opt-in retries for tools/call - Per-tool approvals, HMAC-signed approvals and Open Policy Agent rules in @ai-sdk/policy-opa - Telemetry only after an OpenTelemetry integration is registered, with recordInputs and recordOutputs switches - Tool search with deferred loading, so the model sees only a search tool until it needs more ## Weaknesses - TypeScript only, and `ai` 7.x needs Node 22 or newer - Three major versions between July 2025 and June 2026, each with breaking changes - String model IDs go to Vercel's AI Gateway by default, which needs a Vercel key - No input or output guardrail primitive, and sandboxes and stdio MCP transport are still experimental - 1,399 open issues and pull requests on 4 October 2026, per a GitHub mirror ## Before you call it (notes for agents) 1. Pass a provider instance such as openai('model') if traffic shouldn't go through Vercel's AI Gateway 2. Set toolApproval on tools that write, and experimental_toolApprovalSecret when approvals come back from a browser 3. Raise or replace the default stop condition of 20 steps with stopWhen 4. Close the MCP client after the run, and use HTTP transport outside local development 5. Set recordInputs and recordOutputs to false when spans would carry secrets ## Get started Install: ```bash npm i ai # MCP: npm i @ai-sdk/mcp ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | OpenAI Agents SDK | AA | 86.2 | 3 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/openai-agents-sdk.md | | Pydantic AI | A | 81.9 | 7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/pydantic-ai.md | | Strands Agents | A | 80 | 15 | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | no | https://www.anchorterminal.com/tools/strands-agents.md | | Microsoft Agent Framework | A | 79.4 | 18 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/microsoft-agent-framework.md | | Mastra | BB | 74.2 | 91 | agent.framework, agent.durable, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/mastra.md | | Docker Agent | BB | 73.6 | 101 | agent.framework, agent.multi-agent, agent.mcp-client, agent.durable | no | https://www.anchorterminal.com/tools/docker-agent.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - `ai` 7.0.163 on npm on 2026-11-05, with 226 stable releases across 7.x, 6.x and 5.x in the 90 days to 6 November 2026, and 6.x and 5.x still patched under the ai-v6 and ai-v5 tags (source: ) - Majors 5.0 (2025-07-31), 6.0 (2025-12-22) and 7.0 (2026-06-25), each with a migration guide, and codemods where possible per the versioning page (source: ) - String model IDs resolve through the AI Gateway when no default provider is set (source: ) - Telemetry needs @ai-sdk/otel and registerTelemetry(), and inputs and outputs are recorded unless switched off (source: ) - Two low-severity advisories in the last 12 months, GHSA-rwvc-j5jr-mgvh (2025-11-07, `ai`) and GHSA-866g-f22w-33x8 (2026-05-18, @ai-sdk/provider-utils), both fixed, and none new to 6 November 2026 (source: ) - #1 of 20 in Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md - All 171 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md ## Compare - [AgentOS vs AI SDK](https://www.anchorterminal.com/compare/agentos-vs-vercel-ai-sdk.md): BB 75.8 vs AA 89.8 - [Agno vs AI SDK](https://www.anchorterminal.com/compare/agno-vs-vercel-ai-sdk.md): BB 70.9 vs AA 89.8 - [BoxLang AI vs AI SDK](https://www.anchorterminal.com/compare/boxlang-ai-vs-vercel-ai-sdk.md): B 65.8 vs AA 89.8 - [Claude Agent SDK vs AI SDK](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-vercel-ai-sdk.md): BB 70.3 vs AA 89.8 - [CrewAI vs AI SDK](https://www.anchorterminal.com/compare/crewai-vs-vercel-ai-sdk.md): C 59 vs AA 89.8 - [Cursor Agent SDK vs AI SDK](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-vercel-ai-sdk.md): B 63.7 vs AA 89.8 - [Docker Agent vs AI SDK](https://www.anchorterminal.com/compare/docker-agent-vs-vercel-ai-sdk.md): BB 73.6 vs AA 89.8 - [Agent Development Kit (ADK) vs AI SDK](https://www.anchorterminal.com/compare/google-adk-vs-vercel-ai-sdk.md): B 68.7 vs AA 89.8 - [guilds.run vs AI SDK](https://www.anchorterminal.com/compare/guilds-run-vs-vercel-ai-sdk.md): D 53.4 vs AA 89.8 - [LangGraph vs AI SDK](https://www.anchorterminal.com/compare/langgraph-vs-vercel-ai-sdk.md): B 69.8 vs AA 89.8 - [LlamaIndex Framework vs AI SDK](https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk.md): BB 70 vs AA 89.8 - [Mastra vs AI SDK](https://www.anchorterminal.com/compare/mastra-vs-vercel-ai-sdk.md): BB 74.2 vs AA 89.8 - [Microsoft Agent Framework vs AI SDK](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-vercel-ai-sdk.md): A 79.4 vs AA 89.8 - [OpenAI Agents SDK vs AI SDK](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-vercel-ai-sdk.md): AA 86.2 vs AA 89.8 - [Pydantic AI vs AI SDK](https://www.anchorterminal.com/compare/pydantic-ai-vs-vercel-ai-sdk.md): A 81.9 vs AA 89.8 - [smolagents vs AI SDK](https://www.anchorterminal.com/compare/smolagents-vs-vercel-ai-sdk.md): C 58.7 vs AA 89.8 - [Strands Agents vs AI SDK](https://www.anchorterminal.com/compare/strands-agents-vs-vercel-ai-sdk.md): A 80 vs AA 89.8 - [TradingAgents vs AI SDK](https://www.anchorterminal.com/compare/tradingagents-vs-vercel-ai-sdk.md): C 61.4 vs AA 89.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on ai-sdk.dev or vercel.com or one of their subdomains, or the README at the root of github.com/vercel/ai. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "vercel-ai-sdk", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html AI SDK on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![AI SDK on Anchor Terminal](https://www.anchorterminal.com/badges/vercel-ai-sdk.svg)](https://www.anchorterminal.com/tools/vercel-ai-sdk) ``` Plain link: ```html AI SDK on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say AI SDK is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/vercel-ai-sdk-dark.png - Light: https://www.anchorterminal.com/assets/share/vercel-ai-sdk-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp