Open source anthropic projects

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor

Desktop AI agent with persistent memory across platforms

The agent engineering platform.

🪨 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.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context b

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

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. Li

LLM gateway for auth, load balancing, and spend tracking

AI pair programmer that works inside your terminal

One interface for all your AI models and conversations

⌥ Coding agent with the IDE wired in

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

Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.

📦 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 Langua

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

Build unlimited AI apps locally with zero vendor lock-in

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 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 / Co

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, tas

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

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 v

Open-source LLM tracing & evaluation for AI optimization

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

Voice-to-text that works offline, privately, on any app

~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 pri

🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, single-fil

Self-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, scheduling, failover, request logs and usage. 自托管 AI 网关：

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

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

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

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

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

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Sv

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.

AI API identity gateway — reverse proxy that normalizes device fingerprints and telemetry for privacy-preserving API proxying

README file generator, powered by AI.

Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remote

AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools

the terminal client for LLMs

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no teleme

👻 Proxy API gateway for Kiro IDE & CLI (Amazon Q Developer / AWS CodeWhisperer). Use free Claude models with any client.

Seamless integration between Claude Code AI assistant and Neovim

🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手，也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deploy

Unified API for all LLM providers with analytics

An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama,

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0,

Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never s

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.