GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
vllm-project
A high-throughput and memory-efficient inference and serving engine for LLMs
Python91,383 starslast pushed 24 hours agoopeninterpreter
A coding agent for open models like Kimi K3 and GLM 5.3
Rust68,278 starslast pushed 2 days agodiegosouzapw
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
TypeScript63,592 starslast pushed Yesterdaymindsdb
The unified workspace where open-source models get things done for you.
Makefile39,721 starslast pushed Yesterdayripperhe
xorbitsai
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
Python9,562 starslast pushed 2 days agoolimorris
CommandCodeAI
Command Code AI — the best coding agent for open models.
—3,904 starslast pushed 4 weeks agoliaohch3
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
Python3,188 starslast pushed 2 weeks agoduolahypercho
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
JavaScript3,145 starslast pushed Yesterday
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | vllm-project A high-throughput and memory-efficient inference and serving engine for LLMs | Python | 91,383 | last pushed 24 hours ago | |
| 2 | openinterpreter A coding agent for open models like Kimi K3 and GLM 5.3 | Rust | 68,278 | last pushed 2 days ago | |
| 3 | diegosouzapw Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors | TypeScript | 63,592 | last pushed Yesterday | |
| 4 | mindsdb The unified workspace where open-source models get things done for you. | Makefile | 39,721 | last pushed Yesterday | |
| 5 | ripperhe Bob 是一款 macOS 平台的翻译和 OCR 软件。 | — | 9,744 | last pushed 8 months ago | |
| 6 | xorbitsai Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API. | Python | 9,562 | last pushed 2 days ago | |
| 7 | olimorris ✨ AI Coding, Vim Style | Lua | 6,846 | last pushed 2 days ago | |
| 8 | CommandCodeAI Command Code AI — the best coding agent for open models. | — | 3,904 | last pushed 4 weeks ago | |
| 9 | liaohch3 Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer. | Python | 3,188 | last pushed 2 weeks ago | |
| 10 | duolahypercho External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback. | JavaScript | 3,145 | last pushed Yesterday |
All · 11,474