CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Stars73.7K +112
24h velocity4 sources
Cross-signal scoring · refreshed every 30 minutes
2,000 repos tracked · 89D window · 4M new stars
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
| # | Repository | Stars | 24h | 7d | 30d | Trend | Mentions | Actions |
|---|---|---|---|---|---|---|---|---|
| 01 | 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. | 97.6K | +631+0.7% | +4.5K+4.9% | +22.4K+29.8% |
Pocket workbench for Hermes Agent — limited FOA desk, dual decode, skills+MEMORY fabric, neural FOA. Not J-space. Not a second runtime.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
| 02 | Graphify-Labs/graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. | 97.6K | +498+0.5% | +4.5K+4.9% | +22.4K+29.8% |
| 03 | Lum1104/Understand-Anything 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. | 76.6K | +164+0.2% | +1.1K+1.4% | +6.5K+9.3% |
| 04 | Egonex-AI/Understand-Anything 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. | 76.6K | +140+0.2% | +1.1K+1.4% | +6.5K+9.3% |
| 05 | zeroclaw-labs/zeroclaw Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀 | 32.4K | +16+0.0% | +68+0.2% | +368+1.1% |
| 06 | unslothai/unsloth Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models. | 69K | +17+0.0% | +309+0.4% | +1.6K+2.3% |
| 07 | openclaw/openclaw Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 | 384.4K | +74+0.0% | +707+0.2% | +3.3K+0.9% |
| 08 | NousResearch/hermes-agent The agent that grows with you | 221.8K | +409+0.2% | +3.4K+1.6% | — |
| 09 | Tracer-Cloud/opensre Build your own AI SRE agents. The open source toolkit for the AI era. | 9.4K | +126+1.4% | +520+5.8% | +1.7K+22.5% |
| 10 | Yeachan-Heo/oh-my-codex OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more. | 32.3K | +17+0.1% | +102+0.3% | +860+2.7% |
| 11 | paperclipai/paperclip The open-source app everyone uses to manage agents at work | 75K | +19+0.0% | +534+0.7% | +2.5K+3.4% |
| 12 | warpdotdev/warp Warp is an agentic development environment, born out of the terminal. | 63.7K | +43+0.1% | +218+0.3% | +1.3K+2.0% |
| 13 | MHSanaei/3x-ui Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto) | 43.8K | +75+0.2% | +363+0.8% | +2.1K+5.0% |
| 14 | mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. | 48K | +4+0.0% | +213+0.4% | +761+1.6% |
| 15 | anthropics/claude-plugins-official Official, Anthropic-managed directory of high quality Claude Code Plugins. | 32.8K | +5+0.0% | +323+1.0% | +1.5K+4.9% |
| 16 | ggml-org/llama.cpp LLM inference in C/C++ | 121.9K | +16+0.0% | +621+0.5% | +3.6K+3.0% |
| 17 | anomalyco/opencode The open source coding agent. | 190.5K | +271+0.1% | +2.2K+1.2% | +8.4K+4.6% |
| 18 | BerriAI/litellm The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] | 54.9K | +15+0.0% | +604+1.1% | +3K+5.9% |
| 19 | langchain-ai/deepagents The batteries-included agent harness. | 26.9K | +76+0.3% | +287+1.1% | +1.6K+6.3% |
| 20 | PerryTS/perry A native TypeScript compiler written in Rust. Compiles TypeScript directly to executables using SWC and LLVM. | 4.4K | +15+0.3% | +122+2.9% | +444+11.3% |
| 21 | twentyhq/twenty The open alternative to Salesforce, designed for AI. | 53.8K | +3+0.0% | +333+0.6% | +1.8K+3.5% |
| 22 | garrytan/gbrain Garry's Opinionated OpenClaw/Hermes Agent Brain | 27.3K | +99+0.4% | +508+1.9% | +2.9K+11.8% |
| 23 | HKUDS/DeepTutor DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. | 30.9K | +345+1.1% | +2K+7.0% | +5.8K+23.1% |
| 24 | jdx/mise dev tools, env vars, task runner | 31.2K | +8+0.0% | +220+0.7% | +1K+3.3% |
| 25 | nearai/ironclaw IronClaw is an Agent OS focused on privacy, security and extensibility | 12.6K | +8+0.1% | +25+0.2% | +138+1.1% |
| 26 | diegosouzapw/OmniRoute Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, 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 500+ contributors | 32.9K | +817+2.5% | +9.4K+40.1% | +25.6K+348.7% |
| 27 | Q00/ouroboros Agent OS: Stop prompting. Start specifying. | 5.2K | +15+0.3% | +136+2.7% | +462+9.8% |
| 28 | different-ai/openwork The open-source alternative to Claude Cowork (powered by opencode) | 17.4K | +116+0.7% | +365+2.1% | +837+5.1% |
| 29 | pingdotgg/t3code No description published. | 15.4K | +127+0.8% | +1.2K+8.4% | +2.4K+18.6% |
| 30 | THU-MAIC/OpenMAIC Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click | 20.3K | +61+0.3% | +381+1.9% | +1.4K+7.3% |
| 31 | qdrant/qdrant Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/ | 33.6K | +13+0.0% | +134+0.4% | +883+2.7% |
| 32 | Yeachan-Heo/oh-my-claudecode Teams-first Multi-agent orchestration for Claude Code | 38.1K | +33+0.1% | +188+0.5% | +1.1K+2.9% |
| 33 | rustfs/rustfs 🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph. | 30.3K | +13+0.0% | +219+0.7% | +1K+3.6% |
| 34 | aaif-goose/goose an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM | 51.9K | +98+0.2% | +441+0.9% | +1.5K+2.9% |
| 35 | vectorize-io/hindsight Hindsight: Agent Memory That Learns | 18.9K | +3+0.0% | +192+1.0% | +1.2K+6.7% |
| 36 | QwenLM/qwen-code An open-source AI coding agent that lives in your terminal. | 26.4K | +5+0.0% | +177+0.7% | +792+3.1% |
| 37 | koala73/worldmonitor Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface | 75.8K | +491+0.7% | +10.6K+16.2% | +14.8K+24.3% |
| 38 | CherryHQ/cherry-studio AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs | 49.1K | +10+0.0% | +212+0.4% | +1.2K+2.5% |
| 39 | blakeblackshear/frigate NVR with realtime local object detection for IP cameras | 34.6K | +8+0.0% | +135+0.4% | +599+1.8% |
| 40 | langfuse/langfuse 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 | 32K | +123+0.4% | +438+1.4% | +2.1K+7.0% |
| 41 | 1jehuang/jcode The most RAM effiecent harness | 12.7K | +589+4.9% | +2.4K+23.3% | +4.6K+57.5% |
| 42 | topoteretes/cognee Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine. | 29.5K | +112+0.4% | +492+1.7% | +4.8K+19.6% |
| 43 | openai/codex Lightweight coding agent that runs in your terminal | 102.1K | +239+0.2% | +1.7K+1.7% | +8.2K+8.7% |
| 44 | 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 git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration | 44.7K | +79+0.2% | +284+0.6% | +1.7K+3.8% |
| 45 | K-Dense-AI/scientific-agent-skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard. | 32K | +78+0.2% | +608+1.9% | +2.5K+8.5% |
| 46 | HKUDS/nanobot Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps | 46.3K | +57+0.1% | +326+0.7% | +1.6K+3.5% |
| 47 | iii-hq/iii Effortlessly compose, extend, and observe every service in real-time for the first time ever. | 18.5K | +14+0.1% | +37+0.2% | +185+1.0% |
| 48 | rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies | 73.7K | +112+0.2% | +1.3K+1.8% | +6.4K+9.5% |
| 49 | tailscale/tailscale The easiest, most secure way to use WireGuard and 2FA. | 34.4K | +11+0.0% | +279+0.8% | +1.5K+4.5% |
| 50 | charmbracelet/crush Glamourous agentic coding for all 💘 | 26.9K | +38+0.1% | +203+0.8% | +1.1K+4.2% |