Trending repositories: anthropic

43 tracked repositories tagged with anthropic, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

43 of 43 repositories

  • 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.

    AI summary: An agent harness performance optimization system for AI coding assistants.

    307,889developer-toolsJavaScriptMIT
  • NousResearch/hermes-agent

    The agent that grows with you

    AI summary: Framework to build, deploy, and execute autonomous language model agents equipped with complex reasoning capabilities.

    265,008ai-mlPythonMIT
  • anthropics/claude-code

    Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

    AI summary: An official, terminal-based AI coding assistant powered directly by the Claude model family.

    156,477developer-toolsTypeScript
  • JuliusBrussee/caveman

    why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.

    AI summary: An agent skill and local proxy that reduces LLM token consumption by condensing context and output into concise 'cave...

    121,800ai-mlGoApache-2.0
  • 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

    AI summary: A persistent memory compression system that captures and injects project context into Claude AI sessions.

    118,667ai-mlTypeScriptApache-2.0
  • 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

    AI summary: A free AI gateway providing access to 290+ providers and 500+ models through a single endpoint.

    88,571ai-mlTypeScriptMIT
  • rtk-ai/rtk

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    AI summary: A high-performance CLI proxy written in Rust that radically compresses shell output to reduce LLM context token usage.

    87,213developer-toolsRustApache-2.0
  • 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.

    AI summary: A context compression layer that significantly reduces token usage for AI agents while preserving accuracy.

    80,115ai-mlPythonApache-2.0
  • asgeirtj/system_prompts_leaks

    Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.

    AI summary: An analytical archive of leaked system prompts from major commercial AI applications.

    71,686securityPythonCC0-1.0
  • code-yeongyu/oh-my-openagent

    OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.

    AI summary: A powerful TUI harness and orchestrator for coding agents like Codex and OpenCode, optimized for complex codebases.

    70,987developer-toolsTypeScriptOther
  • shanraisshan/claude-code-best-practice

    from vibe coding to agentic engineering - practice makes claude perfect

    AI summary: A comprehensive collection of optimized prompt patterns for generating code with Anthropic's Claude.

    69,257learningHTMLMIT
  • 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

    AI summary: A curated collection of top-tier resources, skills, and tooling for Anthropic's Claude Code agent.

    58,320developer-toolsPythonOther
  • anthropics/claude-cookbooks

    A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

    AI summary: A collection of recipes and interactive notebooks for building applications with the Claude API.

    54,819learningJupyter NotebookMIT
  • anthropics/claude-plugins-official

    Official, Anthropic-managed directory of high quality Claude Code Plugins.

    AI summary: The official repository for Anthropic's verified plugins for the Claude ecosystem.

    47,626developer-toolsPythonApache-2.0
  • 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

    AI summary: An open-source, highly customizable chat interface supporting multiple AI models simultaneously.

    47,231ai-mlTypeScriptMIT
  • anthropics/financial-services

    AI summary: Reference agents, skills, and data connectors for implementing Claude in financial services workflows.

    41,382otherPythonApache-2.0
  • Donchitos/Claude-Code-Game-Studios

    Turn Claude Code into a full game dev studio — 49 AI agents, 75 workflow skills, and a complete coordination system mirroring real studio hierarchy.

    AI summary: A coordinated multi-agent framework that transforms Claude Code into a complete virtual game development studio.

    40,403developer-toolsShellMIT
  • vxcontrol/pentagi

    Fully autonomous AI Agents system capable of performing complex penetration testing tasks

    AI summary: An autonomous penetration testing platform powered by a multi-agent system for continuous security validation.

    34,687securityGoMIT
  • zarazhangrui/frontend-slides

    Create beautiful slides on the web using a coding agent's frontend skills

    AI summary: A coding-agent skill that generates beautiful, dependency-free HTML presentations using visual style discovery.

    32,696productivityJavaScriptMIT
  • 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.

    AI summary: An AI coding gateway connecting multiple tools to 40+ providers with token-saving features.

    32,610ai-mlJavaScriptMIT
  • jarrodwatts/claude-hud

    A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

    AI summary: A terminal HUD designed for Claude Code to monitor context and tokens in AI coding agents.

    29,255developer-toolsJavaScriptMIT
  • lidge-jun/opencodex

    Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

    AI summary: Universal proxy translating proprietary requests from locked-down AI apps to any local or cloud LLM.

    18,657developer-toolsTypeScriptMIT
  • 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.

    AI summary: An institutional-grade, multi-agent investment research framework combining fundamental analysis with LLM automation.

    17,196dataHTMLMIT
  • The-PR-Agent/pr-agent

    🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.

    AI summary: The Original Open-Source PR Reviewer powered by AI models.

    16,339developer-toolsPythonMIT
  • 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.

    AI summary: A macOS desktop GUI for managing and visualizing Claude Code sessions with interactive tools.

    15,474developer-toolsTypeScriptOther
  • kyegomez/OpenMythos

    A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

    AI summary: A theoretical, open-source reconstruction of the Claude Mythos looped transformer architecture.

    14,931ai-mlPythonMIT
  • cobusgreyling/loop-engineering

    Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

    AI summary: Loop-engineering provides a robust framework for managing complex control flows and agentic loops in LLM applications.

    11,804ai-mlTypeScriptMIT
  • OpenWhispr/openwhispr

    Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

    AI summary: Cross-platform voice-to-text dictation application utilizing local Nvidia Parakeet and Whisper models.

    11,765productivityJavaScriptMIT
  • aden-hive/hive

    Multi-Agent Harness for Production AI

    AI summary: A production-grade execution harness for building, coordinating, and scaling multi-agent AI systems.

    11,169ai-mlPythonApache-2.0
  • 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.

    AI summary: Fully local, agentic AI assistant for deep web research with accurate citations on consumer hardware.

    9,596ai-mlPythonMIT
  • strands-agents/harness-sdk

    Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

    AI summary: An open-source SDK for building and controlling production AI agents end-to-end across any model or cloud provider.

    9,261ai-mlTypeScriptApache-2.0
  • OpenCoworkAI/open-codesign

    Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

    AI summary: A desktop application that utilizes local AI to rapidly generate, edit, and export UI components and landing pages.

    8,236developer-toolsTypeScriptMIT
  • open-multi-agent/open-multi-agent

    Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

    AI summary: TypeScript orchestration framework that dynamically plans and executes tasks using multiple AI agents locally.

    7,069ai-mlTypeScriptMIT
  • BlockRunAI/ClawRouter

    The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

    AI summary: LLM router explicitly built for autonomous AI agents using crypto authentication.

    6,667infrastructureTypeScriptMIT
  • KimYx0207/AI-Coding-Guide-Zh

    Claude Code + OpenClaw + Codex + WorkBuddy 中文教程 | 50篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 四线学习路径(编程+助手+Agent+办公)

    AI summary: A Chinese tutorial suite detailing workflows and enterprise deployment strategies for Claude Code, OpenClaw, and Codex.

    6,523learningPythonMIT
  • op7418/CodePilot

    A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.

    AI summary: An advanced, privacy-focused AI coding assistant delivering a native IDE experience via a desktop Electron app.

    6,520developer-toolsTypeScriptOther
  • nirholas/fresh-start

    Record of the former nirholas/claude-code mirror: the DMCA, the leak timeline and the x402 correction. No Anthropic code

    AI summary: A placeholder repository providing status updates following the DMCA takedown of the original claude-code project.

    6,225otherOther
  • sergebulaev/linkedin-skills

    Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.

    AI summary: A collection of 12 specialized skills for Claude Code and Codex designed specifically to automate LinkedIn marketing.

    6,061productivityPythonMIT
  • michael-denyer/pstack-claude

    Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

    AI summary: An opinionated agent skill stack for Claude Code and Codex to improve autonomous workflows.

    4,560ai-mlJavaScriptMIT
  • composio-community/open-claude-cowork

    Open Source version of Claude Cowork with 500+ SaaS app integrations

    AI summary: Automated workflow application that integrates Claude models to function as an AI co-worker within secure environments.

    4,319ai-mlJavaScriptMIT