Popular projects
2,000 to under 100,000 GitHub stars · most stars first within each tier · Methodology
★ 2,000–under 5,000 · Developer tools · 498 projects
Green numbers beside ★ are stars gained since the previous check · Most stars
- Rank 61
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
★ 4,345+1 - Rank 62
A real browser that runs directly inside your terminal.
★ 4,343+15 - Rank 63
Camunda is the platform for agentic orchestration. Run AI agents, people, and systems as one governed process you can prove and improve. Trusted by 750+ enterprises.
★ 4,343+2 - Rank 64★ 4,330
- Rank 65★ 4,322+3
- Rank 66
Multi-vendor library to simplify Paramiko SSH connections to network devices
Translation pending
★ 4,313 - Rank 67
Petdex is the public gallery of animated pets for coding agents. Works with ChatGPT (Codex), Claude Code, Gemini CLI, OpenCode, Qoder, Kimi Code, CodeBuddy, and OMP. Browse open-source pets, preview t
★ 4,305+3 - Rank 68
Free models included or connect any model from any provider, including Claude, GPT, Gemini and more.
★ 4,302+9 - Rank 69
One place every agent plugs into every tool you already use. Wire it up once, bring the whole team.
★ 4,298+5 - Rank 70★ 4,278+5
- Rank 71
Switch between multiple Claude Code accounts, with automatic rate-limit rotation, usage dashboard, and parallel sessions
★ 4,261 - Rank 72★ 4,255
- Rank 73★ 4,247
- Rank 74
Drake ("dragon" in Middle English) is a C++ toolbox started by the Robot Locomotion Group at the MIT Computer Science and Artificial Intelligence Lab (CSAIL). The development team has now grown signif
★ 4,242 - Rank 75
Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.
★ 4,212+6
