1.affaan-m / ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
+23,859 stars
from 270,933 · score 10.08
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
95 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.thedotmack / claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
+13,897 stars
from 95,321 · score 9.54
3.cheaper-inference / OmniRoute
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ 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 900+ contributors
+11,494 stars
from 72,139 · score 9.35
4.NousResearch / hermes-agent
The agent that grows with you
+9,525 stars
from 249,976 · score 9.16
5.vxcontrol / pentagi
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
+7,923 stars
from 25,020 · score 8.98
6.JuliusBrussee / caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
+7,601 stars
from 109,098 · score 8.94
7.Donchitos / Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
+6,674 stars
from 25,566 · score 8.81
8.headroomlabs-ai / headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+4,495 stars
from 74,072 · score 8.41
9.Louis-CFM / coucou
A tiny friend in your Mac's notch and on your iPhone that keeps an eye on your AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, Antigravity and more. Approve from the notch or your Lock Screen.
+3,745 stars
from 3,136 · score 8.23
10.can1357 / oh-my-pi
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
+3,428 stars
from 34,004 · score 8.14
11.rtk-ai / rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
+3,223 stars
from 82,003 · score 8.08
12.guillaumemeyer / watermarks-remover
A privacy-first app that strips AI watermarks from content you own.
+2,812 stars
from 23,098 · score 7.94
13.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]
+2,579 stars
from 59,920 · score 7.86
14.hesreallyhim / awesome-claude-code
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affiliation). A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins
+2,178 stars
from 54,870 · score 7.69
15.wshobson / agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
+2,013 stars
from 40,068 · score 7.61
16.asgeirtj / system_prompts_leaks
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
+1,999 stars
from 68,597 · score 7.60
17.langchain-ai / langchain
The agent engineering platform.
+1,881 stars
from 146,958 · score 7.54
18.decolua / 9router
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
+1,731 stars
from 30,073 · score 7.46
19.zarazhangrui / frontend-slides
Create beautiful slides on the web using a coding agent's frontend skills
+1,664 stars
from 30,038 · score 7.42
20.shanraisshan / claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
+1,529 stars
from 66,899 · score 7.33
21.nateherkai / scroll-craft
An agent skill for building premium, immersive, scroll-driven websites. Works with Codex, Claude Code, and other coding agents. Also available as a Claude Code plugin.
+1,511 stars
from 2,853 · score 7.32
22.LibreChat-AI / LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
+1,490 stars
from 45,127 · score 7.31
23.code-yeongyu / oh-my-openagent
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
+1,092 stars
from 69,489 · score 7.00
24.CoplayDev / unity-mcp
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
+1,008 stars
from 14,613 · score 6.92
25.jarrodwatts / claude-hud
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
+897 stars
from 28,182 · score 6.80
26.davila7 / claude-code-templates
CLI tool for configuring and monitoring Claude Code
+788 stars
from 32,256 · score 6.67
27.karanb192 / awesome-claude-code-mods
6,000+ Claude Code mods, with what each one can access before you install it. Context and usage meters, prompt cache warmers, status lines, guards and more, with install hints.
+736 stars
from 100 · score 6.60
28.The-PR-Agent / pr-agent
🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
+646 stars
from 13,221 · score 6.47
29.Aider-AI / aider
aider is AI pair programming in your terminal
+644 stars
from 49,241 · score 6.47
30.vercel / ai
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
+627 stars
from 27,053 · score 6.44
31.dyad-sh / dyad
Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!
+562 stars
from 21,589 · score 6.33
32.siteboon / claudecodeui
Use Claude Code, OpenCode, Cursor CLI, and Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and projects remotely.
+512 stars
from 13,867 · score 6.24
33.yamadashy / repomix
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
+511 stars
from 28,600 · score 6.24
34.ThinkWatchProject / ThinkWatch-Lite
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
+502 stars
from 1 · score 6.22
35.NanmiCoder / cc-haha
本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.
+481 stars
from 14,782 · score 6.18
36.travisvn / awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code
+452 stars
from 15,214 · score 6.12
37.wesammustafa / Claude-Code-Everything-You-Need-to-Know
Claude Code guide in three levels, Beginner to Advanced: hands-on lessons with checked exercises, every volatile fact cited to its source. Independent community guide.
+443 stars
from 3,074 · score 6.10
38.xbtlin / ai-berkshire
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
+431 stars
from 16,541 · score 6.07
39.Arize-ai / phoenix
AI Observability & Evaluation
+420 stars
from 11,675 · score 6.04
40.langchain-ai / open-swe
An Open-Source Asynchronous Coding Agent
+394 stars
from 10,767 · score 5.98
41.hamzafer / claude-code-mods
Claude Code mods: plugins built on hooks that add live lines above the prompt, guards, panes and games. Context bar, usage meter, Codex review watch, Markdown preview, Spotify now playing and more.
+387 stars
from 44 · score 5.96
42.Nwflower / dsh-claude-style
Claude Code Desktop theme for DeepSeek Harness｜ 为 DeepSeek Harness 复刻 Claude Code Desktop 风格与交互体验的主题插件
+363 stars
from 68 · score 5.90
43.panxunying / ai-coding-welfare
AI Coding 福利站导航：免费白嫖 Claude Code / Codex 的中转站与公益站合集，含额度、模型、价格自动更新与一键配置脚本
+356 stars
from 861 · score 5.88
44.LearningCircuit / local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
+348 stars
from 9,128 · score 5.86
45.simstudioai / sim
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
+261 stars
from 29,700 · score 5.57
46.tjboudreaux / cc-thinking-skills
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
+238 stars
from 1,455 · score 5.48
47.IvanMurzak / Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
+200 stars
from 4,366 · score 5.30
48.langchain4j / langchain4j
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
+163 stars
from 13,175 · score 5.10
49.aden-hive / hive
Multi-Agent Harness for Production AI
+97 stars
from 11,034 · score 4.58
50.mnfst / llm-gateway
Open Source LLM Gateway 🦚
+78 stars
from 7,534 · score 4.37
51.winfunc / opcode
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
+66 stars
from 22,366 · score 4.20
52.crmne / ruby_llm
The Ruby AI framework.
+66 stars
from 4,424 · score 4.20
53.IvanMurzak / Godot-MCP
Godot-MCP — Model Context Protocol (MCP) integration for the Godot Engine. AI tools for the Godot Editor in C#, with cloud connection to ai-game.dev. Apache-2.0.
+56 stars
from 264 · score 4.04
54.olimorris / codecompanion.nvim
✨ AI Coding, Vim Style
+55 stars
from 6,864 · score 4.03
55.ferrumclaudepilgrim / claude-code-android
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.
+52 stars
from 257 · score 3.97
56.kyegomez / OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
+51 stars
from 14,863 · score 3.95
57.stackblitz / bolt.new
Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz
+45 stars
from 16,539 · score 3.83
58.jazzyalex / agent-sessions
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across Codex, Claude Code, OpenCode, Cursor Agent, Antigravity, Hermes, OpenClaw, Copilot CLI, and more.
+43 stars
from 888 · score 3.78
59.coipond / coi
Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.
+42 stars
from 728 · score 3.76
60.vostride / agent-qa
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
+38 stars
from 877 · score 3.66
61.xonsh / xonsh
🐚 Python-powered shell. Full-featured, cross-platform and AI-friendly.
+37 stars
from 9,647 · score 3.64
62.roomi-fields / notebooklm-mcp
Google Gemini Notebook (formerly NotebookLM) over MCP + a local HTTP REST API. Citation-backed Q&A, full Studio generation, chat history, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.
+31 stars
from 187 · score 3.47
63.ypollak2 / llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
+27 stars
from 93 · score 3.33
64.activeloopai / hivemind
Hivemind turns your traces into reusable skills across agents
+24 stars
from 1,616 · score 3.22
65.josstei / maestro-orchestrate
Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools
+22 stars
from 463 · score 3.14
66.utensils / mcp-nixos
MCP-NixOS - Model Context Protocol Server for NixOS resources
+21 stars
from 849 · score 3.09
67.zendev-sh / goai
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
+16 stars
from 217 · score 2.83
68.Rich627 / whatsapp-claude-plugin
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
+16 stars
from 99 · score 2.83
69.eli64s / readme-ai
README file generator, powered by AI.
+13 stars
from 2,993 · score 2.64
70.leeguooooo / claude-code-usage-bar
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
+13 stars
from 374 · score 2.64
71.bytebot-ai / bytebotArchived
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
+12 stars
from 11,054 · score 2.56
72.IvanMurzak / Unreal-MCP
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
+12 stars
from 42 · score 2.56
73.tensorzero / tensorzeroArchived
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
+10 stars
from 11,700 · score 2.40
74.congmnguyen / claude-code-wsl2-setup
Guides and scripts for Claude Code on WSL2: screenshot paste, Windows notifications, LSP, and statusline.
+5 stars
from 50 · score 1.79
75.anneschuth / claude-threads
Think of it as screen-sharing for AI pair programming, but everyone can type.
+5 stars
from 41 · score 1.79
76.grooverLab / fable
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
+5 stars
from 14 · score 1.79
77.xberg-io / liter-llm
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
+4 stars
from 259 · score 1.61
78.AgentsKit-io / agentskit
The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.
+4 stars
from 34 · score 1.61
79.aiqualitylab / ai-natural-language-tests
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
+4 stars
from 23 · score 1.61
80.briansmith80 / claude-code-status-bar
Configurable status bar for Claude Code: usage limits with pacing markers, context window, git state, live activity, session cost, and 8 colour themes. Pure bash, zero dependencies.
+4 stars
from 18 · score 1.61
81.HeyRenan / showreel
Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites, one command each. Self-contained Chromium, self-validated output, no MCP.
+4 stars
from 10 · score 1.61
82.mag123c / toktrack
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
+3 stars
from 193 · score 1.39
83.thousandflowers / skillreaper
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
+3 stars
from 59 · score 1.39
84.JoakimCarlsson / ai
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
+3 stars
from 45 · score 1.39
85.yeaight7 / awesome-ai-devtools
The open-source map of the AI developer tooling ecosystem
+3 stars
from 10 · score 1.39
86.agents-squads / squads-cli
CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.
+2 stars
from 54 · score 1.10
87.xvary-research / claude-code-stock-analysis-skill
Claude Code stock analysis skill: SEC EDGAR + market data, /analyze /score /compare — free, local Python tools. By XVARY Research.
+2 stars
from 17 · score 1.10
88.vdalhambra / financekit-mcp
Financial Market Intelligence MCP Server — stock quotes, technical analysis, crypto data, and portfolio insights for AI agents
+2 stars
from 7 · score 1.10
89.Flemma-Dev / flemma.nvim
AI knowledge workbench for Neovim.
+1 stars
from 57 · score 0.69
90.Imolatte / claude-cli-telegram
Turn your Mac/Linux into a remote Claude Code terminal via Telegram. Spawns real CLI — sessions, streaming, approvals, voice, git panel, 30+ commands.
+1 stars
from 35 · score 0.69
91.fabioconcina / claumon
Claude Code dashboard: see where your limits are headed before you hit them. Calibrated usage forecasts, live rate-limit gauges, session costs, memory browser. Single binary, zero config, plus a VS Code extension.
+1 stars
from 16 · score 0.69
92.wei18 / Upkeep
Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.
+1 stars
from 15 · score 0.69
93.labzink / cc-probeline
See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.
+1 stars
from 11 · score 0.69
94.EricAndrechek / Pacer
Native macOS app for tracking Claude Code usage — tokens, cost, rate-limit pacing, per-project breakdowns. SwiftUI + SwiftData.
+1 stars
from 10 · score 0.69
95.sara-star-quant / presence
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
+1 stars
from 7 · score 0.69