updated 2026-10-09 08:15 UTC

Vercel AI SDK

Repository Website by vercel

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Agent Frameworks TypeScript Listed NOASSERTION

Is Vercel AI SDK safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 7.4 / 10
Provenance Attested
Signed commits 100%
Last push today
Advisories None known
Compare Vercel AI SDK

How does it stack up against its Agent Frameworks neighbours?

Pick any agent to compare →
Suggest a correction

In detail: Vercel AI SDK scores 96.2/100 (Grade A), ranked #2 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 7.4/10; 100% of recent commits are signed; no published advisory affects its latest release (ai); last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →

How Vercel AI SDK could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships Vercel AI SDK and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Signed

    github.com/vercel/ai, NOASSERTION, last pushed 2026-10-09. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Strong

    OpenSSF Scorecard rates the repository's practices 7.4/10 (scanned Oct 5, 2026). The checks that decide who can get a change released:

    • Code Review10
    • Branch Protection4
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions10
    • Pinned Dependencies9
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 4
    CI-Tests 10
    CII-Best-Practices 5
    Code-Review 10
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 9
    Maintained 10
    Packaging -1
    Pinned-Dependencies 9
    SAST 0
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 10
    Vulnerabilities 0

  3. Published packages Linked and attested

    • npm ai Source link points back to this repo Build provenance attested

  4. What you install today No known advisories

    Latest release checked: ai 7.0.136. No published advisory affects it (OSV, checked 2026-10-09).

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Vercel AI SDK.

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions

Verify this score yourself

Every build re-issues Vercel AI SDK’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How Vercel AI SDK compares in Agent Frameworks

  1. #1 Haystack 96.3 +0.1
  2. #2 Vercel AI SDK 96.2 this agent
  3. #3 OpenAI Agents SDK (JS) 94.1 −2.1
  4. #4 LangGraph 94.0 −2.2
  5. #5 OpenAI Agents SDK 91.5 −4.7

Bars show each HVTrust score; the tick marks Vercel AI SDK’s 96.2.

Where the 96.2 comes from

HVTrust dimensions vs the Agent Frameworks average

96.2 / 100 · 100.0% confidence

Vercel AI SDK Agent Frameworks average (129 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
21.7 / 25
12.2 above avg 9.5
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
6.4 above avg 11.6
Transparency50% declared license · 50% OSSF Scorecard
14.8 / 17
2.8 above avg 12.0
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
6.4 above avg 13.6
AdoptionLog-scaled stars · package downloads
20.0 / 20
9.2 above avg 10.8

Quick Trust Read

What Would Improve It
Improve safety / integrity to lift the weakest part of the trust profile.
Maintainer Checklist
Keep signals current Trust posture is already in a healthy range. The main job is to keep provenance, maintenance, and public evidence fresh.
Compare with Haystack Get email alerts for Vercel AI SDK View Agent Frameworks Report missing data
93.9
Activity sub-score · out of 100
#2
In Agent Frameworks

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-09 08:15 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
27.2k
Forks
5.3k
Last Push
2026-10-09
today
Commits (4 wk)
608
Downloads (7d)
33,670,560
npm
HN mentions (30d)
6
Open Issues
478
Rank Change
=
was #2

Analysis

Activity Inputs

93.9 / 100
StarsRepository reach
26.6 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
17.3 / 20

Common questions about Vercel AI SDK

Public supply-chain signals for Vercel AI SDK are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but Vercel AI SDK carries less obvious unverified-evidence risk than projects with thin signals.
Does Vercel AI SDK publish package provenance?
Yes. Vercel AI SDK's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does Vercel AI SDK have an OpenSSF Scorecard?
Vercel AI SDK has an OpenSSF Scorecard score of 7.4/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Vercel AI SDK actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Vercel AI SDK use?
Vercel AI SDK ships under NOASSERTION. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Vercel AI SDK's commits signed?
100% of the last 100 commits to Vercel AI SDK are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

Compare Vercel AI SDK head-to-head

Vercel AI SDK vs Haystack → Vercel AI SDK vs OpenAI Agents SDK (JS) → Vercel AI SDK vs LangGraph →

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
high confidence
Implemented
Vercel AI SDK appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
medium confidence
1 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
None detected
No clear plugin system or broad tool surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain Vercel AI SDK?

For maintainers

HVTrust scores Vercel AI SDK from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
HVTrust 2Rank 2Grade 2
2026-09-05
Grade Changed
Trust grade B → A
2026-09-05
Rank Moved
Rank rose 225 spots (#226 → #1)
2026-09-05
HVTrust Changed
HVTrust up 26.4pts (70.0 → 96.4)
2026-09-03
Grade Changed
Trust grade A → B
2026-09-03
Rank Moved
Rank dropped 218 spots (#2 → #220)
2026-09-03
HVTrust Changed
HVTrust down 26.4pts (96.4 → 70.0)
GitHub → Website → npm: ai

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 96.2 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/vercel-ai-sdk.svg)](https://hvtracker.net/agents/vercel-ai-sdk)
HTML:
<a href="https://hvtracker.net/agents/vercel-ai-sdk"><img src="https://hvtracker.net/badge/vercel-ai-sdk.svg" alt="HVTrust"></a>

Other agents in Agent Frameworks

Data sources
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON