Solid machine-oriented AI SDK with strong type safety and test infrastructure, but bloated file count and missing root documentation constrain agent autonomy.
Readiness lenses
The same repo, two ways: how ready it is for an AI coding agent, and for a human newcomer. Switch lenses to see each one's score and checks.
How ready the repo is for an AI coding agent to read, build, and operate it.
73 / 1009 of 18 checks passed across 6 categories.
Machine Orientation
78Solid machine orientation with a comprehensive AGENTS.md, clear monorepo structure, and explicit build/test commands, but missing a root README.md and env example undermines agent navigation confidence.
Reasoning available in the full report.Reproducible Setup
76Solid reproducibility with explicit pinned versions, lockfile, and pnpm-enforced setup; minor gaps in container/documentation clarity and floating Node.js constraint.
Reasoning available in the full report.Code Navigability
72Clear monorepo structure with strong module boundaries and TypeScript strict mode, but vague naming conventions and missing architectural documentation make localization error-prone.
Reasoning available in the full report.Verification Surface
72Strong test and type infrastructure with Turbo, Vitest, TypeScript strict mode, and linting; CI config and exact pinning aid reproducibility, but CI workflows themselves are not visible in the snapshot and test coverage is not quantified.
Reasoning available in the full report.Agent Safety
72Strong secret hygiene and safety controls; missing explicit agent-safety documentation and SECURITY.md undermines trust in disclosed threat handling.
Reasoning available in the full report.Context Economy
62A large, well-structured monorepo with clear tooling and TypeScript strict mode, but no .gitignore-based exclusion markers for generated build outputs and a massive file count (7157) that forces an agent to sift through substantial noise.
Reasoning available in the full report.
Machine Orientation
1 check passed2 problems found
6 more checks in the full report.
Reproducible Setup
1 check passed2 problems found
4 more checks in the full report.
Code Navigability
1 check passed2 problems found
2 more checks in the full report.
Verification Surface
3 checks passed0 problems found
4 more checks in the full report.
Agent Safety
2 checks passed1 problem found
4 more checks in the full report.
Context Economy
1 check passed2 problems found
1 more check in the full report.
How ready the repo is for a human newcomer to understand, set up, and contribute.
75 / 10012 of 18 checks passed across 6 categories.
First Impression
78Well-structured README with clear purpose, unified API examples, and multiple use cases; lacks maturity signals (roadmap, stability badges, architectural overview) and demo/live playground link.
Reasoning available in the full report.Getting Running
68Essentials exist but require tribal knowledge to bridge critical gaps: lockfile is missing from repo, floating Node version in engines, no env.example for examples, and monorepo setup demands pre-reading CONTRIBUTING before any build works.
Reasoning available in the full report.Finding Your Way
68Large monorepo with clear module layout and TypeScript strict typing, but no top-level architecture doc, inconsistent naming across 67+ packages, and weak inline documentation make navigation difficult for newcomers.
Reasoning available in the full report.Path to Contribute
72Comprehensive CONTRIBUTING guide and PR template present; issue templates missing and no beginner-labeled issues or legal disclaimer checks halt a higher score.
Reasoning available in the full report.Signs of Life
85A mature, well-staffed project with active CI, frequent commits, responsive issue handling, and organized release automation via Changesets — minor gaps in contributor documentation and explicit governance.
Reasoning available in the full report.Open Door
85Legal cover, conduct rules, and help channels all present and explicit; missing only a PR template to round out contributor friction points.
Reasoning available in the full report.
First Impression
2 checks passed1 problem found
3 more checks in the full report.
Getting Running
1 check passed2 problems found
4 more checks in the full report.
Finding Your Way
1 check passed2 problems found
2 more checks in the full report.
Path to Contribute
3 checks passed0 problems found
3 more checks in the full report.
Signs of Life
3 checks passed0 problems found
2 more checks in the full report.
Open Door
2 checks passed1 problem found
1 more check in the full report.
Where the grip slips
22 more issues found — each with a concrete fix.
Unlock the full report
See all 23 issues with concrete fixes and the reasoning behind every score. One-off, tied to your account so it works on every device — sign in with GitHub to buy. The score and badge stay free.
Show your score
[](https://latch.fyi/vercel/ai)Share this analysis
https://latch.fyi/vercel/aiFixed some issues? Re-analyze to measure your progress →
Copy the whole report
Grab the entire verdict in one go — a Markdown block for a README or an issue, plain text, or a prompt you can paste straight into an LLM.