vercel-labs/opensrc

Fetch source code for npm packages to give AI coding agents deeper context

View on GitHub ↗Jump to charts ↓

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 32 minutes ago
Added to GitGenius on September 23rd, 2026
Created on January 6th, 2026
Open Issues & Pull Requests: 23 (+0)
GitHub issues: Enabled
Number of forks: 194
Total Stargazers: 3,011 (+0)
Total Subscribers: 12 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 29.7 days
Mean response time: 33.1 days
90th percentile: 56.0 days
Tracked items: 15

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 8
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 152 days
Stale 30+ days: 7
Stale 90+ days: 7

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

opensrc is a CLI tool that fetches and caches source code from npm packages to provide AI coding agents with deeper context for code generation and analysis tasks.

The tool solves the problem of AI agents lacking access to package implementations when working with dependencies. It works by fetching source code from multiple package registries—npm, PyPI, crates.io, and GitHub—and caching the results locally. On first invocation with a package path, opensrc downloads the source; subsequent calls return the cached version instantly, avoiding repeated network requests and enabling agents to reason about actual package behavior rather than relying solely on documentation or type definitions.

Developers building AI-powered coding assistants or agents should consider opensrc if they need their systems to access real implementation details of dependencies. The tool is particularly suited for projects where understanding package internals improves code generation quality. It supports multiple language ecosystems through its registry integrations, making it useful across polyglot development environments. The project is positioned as an experiment from Vercel Labs, indicating it is exploratory work rather than a production-hardened tool.

The project is organized as a Turborepo monorepo with pnpm workspaces, containing a Rust-based CLI implementation and a Next.js documentation site. Development requires Node.js and pnpm, with the CLI component written in Rust while the broader project infrastructure uses JavaScript tooling. The codebase maintains both command-line functionality and comprehensive documentation as first-class components of the repository structure.