Popular projects
2,000 to under 100,000 GitHub stars · most stars first within each tier · Methodology
★ 5,000–under 10,000 · All categories · 376 projects
Green numbers beside ★ are stars gained since the previous check · Most stars
- Rank 16
Free, open-source review tooling for Claude Code, OpenCode, Codex, Pi, and Droid. Review agent plans before they execute, annotate agent-written code, and send structured feedback back locally.
★ 9,755+17 - Rank 17
Lean is an open-source programming language and proof assistant that enables correct, maintainable, and formally verified code.
★ 9,749+16 - Rank 18★ 9,735+5
- Rank 19★ 9,711+3
- Rank 20
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
★ 9,695+28 - Rank 21
The Xonsh shell is a Python-powered shell. Full-featured, cross-platform and AI-friendly.
★ 9,684−1 - Rank 22
View and compare GitHub star history graph of open source projects.
★ 9,674+3 - Rank 23
Anarlog is the open-source, privacy-first, local-first alternative to Granola AI. Take notes during private meetings, turn them into editable summaries, and keep your local meeting data and AI stack u
★ 9,620+1 - Rank 24
CLI for Git worktree management, designed for parallel AI agent workflows.
Translation pending
★ 9,555+12 - Rank 25★ 9,549+4
- Rank 26
A React-first slide framework authored by AI agents. Each page is arbitrary code on a 1920×1080 canvas — versioned, reviewable, yours.
★ 9,461+11 - Rank 27
The programming language for agents
★ 9,453+2 - Rank 28
Command-line interactive multitool for tabular data.
Translation pending
★ 9,428 - Rank 29★ 9,406
- Rank 30
An open table format for huge analytic datasets, letting engines like Spark
Translation pending
★ 9,386+5
