Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Stars30.4K +120
24h velocity5 sources
Cross-signal scoring · refreshed every 30 minutes
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
| # | Repository | Stars | 24h | 7d | 30d | Trend | Mentions | Actions |
|---|---|---|---|---|---|---|---|---|
| 01 | millionco/react-doctor Your agent writes bad React. This catches it | 11.2K | +12+0.1% | +41+0.4% | +422+3.8% |
| 02 | heygen-com/hyperframes Write HTML. Render video. Built for agents. | 21.8K | +12+0.1% | +132+0.6% | +913+4.2% |
| 03 | superset-sh/superset Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine | 11.4K | +3+0.0% | +48+0.4% | — |
| 04 | warpdotdev/warp Warp is an agentic development environment, born out of the terminal. | 60.3K | +13+0.0% | — | +3.2K+5.3% |
| 05 | larksuite/cli The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills. | 12.9K | +11+0.1% | +71+0.5% | +343+2.7% |
| 06 | Yeachan-Heo/oh-my-claudecode Teams-first Multi-agent orchestration for Claude Code | 35.1K | +10+0.0% | +65+0.2% | +330+0.9% |
| 07 | multica-ai/multica The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. | 33.8K | +28+0.1% | +314+0.9% | +1.1K+3.2% |
| 08 | QwenLM/qwen-code An open-source AI agent that lives in your terminal. | 24.7K | +3+0.0% | +32+0.1% | — |
| 09 | volcengine/OpenViking OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving. | 24.8K | +4+0.0% | +37+0.1% | — |
| 10 | soxoj/maigret 🕵️♂️ Collect a dossier on a person by username from 3000+ sites | 30.7K | +21+0.1% | +85+0.3% | +1.4K+4.5% |
| 11 | refactoringhq/tolaria Desktop app to manage markdown knowledge bases | 11.6K | +6+0.1% | +48+0.4% | +487+4.2% |
| 12 | abhigyanpatwari/GitNexus GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration | 40.5K | +10+0.0% | +113+0.3% | +1K+2.6% |
| 13 | github/awesome-copilot Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. | 34K | +6+0.0% | +47+0.1% | +243+0.7% |
| 14 | pingdotgg/t3code No description published. | 12.1K | +5+0.0% | +24+0.2% | +149+1.2% |
| 15 | Wei-Shaw/sub2api Sub2API 一站式开源中转服务,让 Claude、Openai 、Gemini、Antigravity订阅统一接入,支持拼车共享,更高效分摊成本,原生工具无缝使用。 | 24K | +9+0.0% | +127+0.5% | +753+3.1% |
| 16 | twentyhq/twenty The open alternative to Salesforce, designed for AI. | 47.5K | +9+0.0% | +101+0.2% | +187+0.4% |
| 17 | aaif-goose/goose an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM | 46K | +4+0.0% | +32+0.1% | +256+0.6% |
| 18 | JimLiu/baoyu-skills No description published. | 19.7K | +5+0.0% | +59+0.3% | +298+1.5% |
| 19 | jundot/omlx LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar | 15.4K | +5+0.0% | +62+0.4% | +400+2.6% |
| 20 | Yeachan-Heo/oh-my-codex OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more. | 29.8K | +7+0.0% | +63+0.2% | +340+1.1% |
| 21 | rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies | 55.4K | +24+0.0% | +234+0.4% | +1.6K+2.8% |
| 22 | pbakaus/impeccable The design language that makes your AI harness better at design. | 30.8K | +12+0.0% | +130+0.4% | +775+2.5% |
| 23 | anthropics/knowledge-work-plugins Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork | 17.4K | +37+0.2% | +393+2.3% | +484+2.8% |
| 24 | anthropics/claude-plugins-official Official, Anthropic-managed directory of high quality Claude Code Plugins. | 28.3K | +14+0.0% | +773+2.7% | +991+3.5% |
| 25 | THU-MAIC/OpenMAIC Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click | 18K | +3+0.0% | +29+0.2% | +170+0.9% |
| 26 | lsdefine/GenericAgent Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption | 12.2K | +3+0.0% | — | +506+4.1% |
| 27 | 1jehuang/jcode Coding Agent Harness | 6.6K | +2+0.0% | +16+0.2% | +752+11.4% |
| 28 | vectorize-io/hindsight Hindsight: Agent Memory That Learns | 14.9K | +9+0.1% | +77+0.5% | +367+2.5% |
| 29 | tinyhumansai/openhuman Your Personal AI super intelligence. Private, Simple and extremely powerful. | 29K | +34+0.1% | +533+1.8% | +2.2K+7.6% |
| 30 | coreyhaines31/marketingskills Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering. | 30.8K | +7+0.0% | +91+0.3% | +541+1.8% |
| 31 | Gitlawb/openclaude runs anywhere. uses anything | 27.9K | +3+0.0% | +48+0.2% | +306+1.1% |
| 32 | vercel-labs/agent-browser Browser automation CLI for AI agents | 34.5K | +7+0.0% | +49+0.1% | +340+1.0% |
| 33 | langchain-ai/deepagents The batteries-included agent harness. | 23.4K | +5+0.0% | — | — |
| 34 | Tencent/WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. | 15.6K | +3+0.0% | +31+0.2% | +130+0.8% |
| 35 | K-Dense-AI/scientific-agent-skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Antigravity, and the open Agent Skills standard. | 26.3K | +12+0.0% | +123+0.5% | +624+2.4% |
| 36 | floci-io/floci Light, fluffy, and always free - The AWS Local Emulator alternative | 13.2K | +4+0.0% | — | +743+5.6% |
| 37 | safishamsi/graphify AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. | 55.1K | +26+0.0% | +397+0.7% | +1.9K+3.4% |
| 38 | garrytan/gbrain Garry's Opinionated OpenClaw/Hermes Agent Brain | 19.5K | +13+0.1% | +131+0.7% | +727+3.7% |
| 39 | EveryInc/compound-engineering-plugin Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more | 17.6K | +14+0.1% | +41+0.2% | +182+1.0% |
| 40 | github/spec-kit 💫 Toolkit to help you get started with Spec-Driven Development | 106.6K | +2+0.0% | — | +1.5K+1.4% |
| 41 | D4Vinci/Scrapling 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! | 54.6K | +12+0.0% | — | +1.7K+3.2% |
| 42 | mattpocock/sandcastle Orchestrate sandboxed coding agents in TypeScript with sandcastle.run() | 5.2K | +6+0.1% | +53+1.0% | +379+7.2% |
| 43 | koala73/worldmonitor Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface | 55K | +2+0.0% | +44+0.1% | +218+0.4% |
| 44 | rohitg00/agentmemory #1 Persistent memory for AI coding agents based on real-world benchmarks | 18.9K | +25+0.1% | +345+1.8% | +1.4K+7.6% |
| 45 | ryoppippi/ccusage Analyze coding (agent) CLI token usage and costs from local data. | 14.9K | +9+0.1% | +30+0.2% | +125+0.8% |
| 46 | HKUDS/nanobot Lightweight, open-source AI agent for your tools, chats, and workflows. | 43.3K | +3+0.0% | +33+0.1% | +205+0.5% |
| 47 | antirez/ds4 DeepSeek 4 Flash local inference engine for Metal and CUDA | 12.2K | +13+0.1% | +100+0.8% | +1.3K+11.0% |
| 48 | cocoindex-io/cocoindex Incremental engine for long horizon agents 🌟 Star if you like it! | 10.1K | +4+0.0% | — | +350+3.5% |
| 49 | mksglu/context-mode Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms | 15.8K | +4+0.0% | +43+0.3% | +506+3.2% |
| 50 | webadderallorg/Recordly Create polished screen recordings without editing. Mac/Windows/Linux | 15.2K | +4+0.0% | +63+0.4% | +529+3.5% |