Code agents

Run parallel Claude Code agents in tmux with automatic permission approval. Auto-approves Bash, WebFetch, and other tool prompts so agents run unattended. One-liner install for macOS, Linux, WSL and Termux.

Decision-quality pre-commitment analysis. Hosted at azimuth-testbed.netlify.app — no install required. Claude Code skill for permanent workflow integration.

Track AI-generated code at line-level granularity. Know which lines were written by AI, modified by humans, and what prompts generated them. Git-native storage, automatic redaction, and Claude Code integration.

Beautiful, themed HTML data displays and research briefings for you and your coding agents.

Configuration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.

Benchmark harness for A/B testing Claude Code plugins against OOLONG long-context reasoning tasks. Compare truncation vs RLM-RS recursive chunking strategies. Features Claude Code hooks integration, SQLite persistence, and comprehensive scoring aligned with the OOLONG paper methodology.

A local MCP server that gives Claude Code persistent context and code intelligence. Sessions, code search, goal tracking, and background analysis — all in two SQLite files.

AI persona avatars + virtual meetings for Claude Code (tmux split-panes + Ralph loop + auto Word/PowerPoint output)

MCP server for Claude Code CLI with full Google Workspace integration - Docs, Sheets, Drive, Gmail, Calendar & Apps Script (72 tools)

Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

Force any OpenAI-compatible or Anthropic API-compatible tool (Claude Code, Qwen Code, Aider, Fabric, Interpreter) to use Gemini, Groq, Cerebras, or Ollama. Pure Bash. Zero dependencies.

Trekoon is a Bun-powered CLI focused on execution workflows where AI agents and humans share the same task graph.

Open-source AI career assistant built with Rust, Tauri, React, and Ollama for resumes, interviews, ATS analysis, and productivity.

LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.

Long Long Run (LLR) is a plug-and-play Codex skill for serious long-running agent tasks: an agent-first harness runtime with INC intent-noise cancellation, ACTIVE durable mainlines, side-thread tolerance, and Codex hook-enforced stop guards.

Self-hosted AI OS: RAG · multi-LLM failover · visual Workflow Studio · Skill Market · multi-tenant workspaces · sandboxed tools · multi-channel (Slack/Discord/Telegram/Feishu) · full observability — one docker compose up

Build UX and design skills for AI agents to improve research, heuristics, and design decisions in Claude Code, Cursor, and Codex

Agent-drivable Patchright browser daemon with a persistent Chrome profile AND a built-in human-behavior layer (realistic mouse paths, keystroke cadence, scroll physics). Gives AI coding agents a real browser they can steer with one-shot CLI calls.

Agent Skill for GitHub repository setup and platform-specific features | Claude Code compatible

One sales agent. Your CRM (sqlite/hubspot/close/attio/salesforce) or none. Your channels (gmail, linkedin). Runs on any MCP-capable harness.

The coffee break for programmers using AI coding agents. 30 seconds to post a vibe, scroll a random feed of devs stuck on the same bugs, react with emoji, get back to work. Powered by GitHub Issues. No server, no signup.

Global CLAUDE.md: Behavior guidelines that stop your agent from overengineering, hallucinating, and breaking things

AI Customer Support Agent with RAG + Voice A fully local, privacy-focused AI customer support system powered by open-source models. It supports multi-turn conversations, PDF/manual search (RAG), product recommendations, FAQ reasoning, and voice input/output using local STT + TTS. Built with Mistral 7B GGUF, FAISS, Whisper Tiny, Coqui TTS, FastAPI.

Take your ChatGPT chats with you. A local-first AI companion with chat import, semantic memory, agentic skills, and full autonomy.

The simplest AI-ready secrets manager. Local-first, single-binary CLI & Desktop app with MCP integration. Never expose secrets to AI agents.

Agentic workflow plugins for tasks you'd rather not do yourself. Someone has to secure your secrets, sort your inbox, and tell you when you're wrong. It's not going to be you.

Open-source web search API for AI agents. Tavily-compatible. Apache 2.0, self-hostable on Cloudflare Workers. 10× cheaper.

AI-powered multi-agent financial advisor system with LangGraph orchestration across nine specialized agents including retrieval, portfolio analysis, market desk, due diligence, and compliance, routing through a LiteLLM gateway, computing real portfolio risk metrics, and holding risky answers for human review before they reach the user.

Keep your secrets out of your AI coding agents. A local HTTPS proxy that swaps real credentials with placeholders and injects them at the network boundary.

Self-correction engine for AI coding agents - implements the Reflexion paper (Shinn et al., 2023) as a Rust MCP server. Turns failures into persistent, searchable lessons that prevent the same mistakes across sessions.

An AI-driven research workflow for generating ideas, running experiments, and writing scientific papers.

deepagents-showcase is a hands-on project demonstrating how to build hierarchical, multi-step AI systems using LangChain’s Deep Agents. It showcases task decomposition, planning, sub-agent delegation, and long-running workflows in a practical, real-world setup.

A full-stack web application that automates the extraction of job postings from career websites and generates personalized cold emails using AI agents. Built with React frontend and FastAPI backend powered by CrewAI and LangChain.

Agenetic AI & GenAI (Groq, Mistral, LangChain, LangGraph, RAG, Vector DBs), Cloud (GCP, AWS, Kubernetes, GKE, ECS Fargate), DevOps/LLMOps (Docker, Jenkins, GitOps, ArgoCD, Prometheus, Grafana, ELK Stack), CI/CD, Security, and Observability.

Manage your work across multiple agents

npx agent-loadout — one command to bootstrap your terminal for agentic coding. 50 CLI tools with companion Skills to inform your agents.

Clippy resurrected as an AI front end. 📃📎👀

Private, secure, AI chatbot interface to serve locally or host on an HTML. This simplified interface and minimal file format aims to provide a framework easily built and expanded on as the field of AI continues to grow. Highly customizable with a visual editor. Currently in the early stages: Development is happening rapidly.

Privacy-first local AI model comparison platform with blind evaluation, per-model hyperparameters, and multi-configuration testing. Compare 2-6 models side-by-side through Ollama with zero cloud dependencies.

Telegram Bot Customer Service Platform - Multi-bot pool, bidirectional messaging, FAQ engine (8 modes + AI), real-time web chat, user management. Python/FastAPI + React/TypeScript + PostgreSQL + Redis. Docker deployable.

CLI tool for evaluating and comparing AI models across Google, Ollama, OpenRouter, LM Studio, LlamaBarn, and GitHub Models. Features robust error handling, cost tracking, memory-augmented chat, and dynamic test coverage.

Self-hosted LLM API benchmark, monitoring & playground. Compare latency, TTFT, throughput across OpenAI, Anthropic, Gemini & any OpenAI-compatible endpoint. Deploy with one command via Docker. | 自托管 LLM API 性能测试、监控与调试平台，一键 Docker 部署，支持多家服务商对比。

🎯 Optimize LLM token usage by 70-90% with smart context ranking, reducing costs while maintaining quality and performance.

Comparison case study between Gliner V2 vs OpenAI Privacy filter model for PII Redaction

Universal LLM protocol middleware for OpenAI, Anthropic, Claude Code, and OpenAI-compatible backends.

Open-source AI + data cost intelligence — 18 connectors (Claude, GPT, Gemini, dbt, warehouses, BI, cloud, CI/CD), cache-tier visibility, anomaly detection, MIT licensed

An eval harness and report on some of the latest LLMs that can be run locally

Find B2B prospects the moment they're in-market. Six Claude Code skills that detect buying signals, surface the accounts showing them, and write outreach that references something real.

Open-source CLI for syncing Claude Code and Codex session transcripts — backup, search, and share your AI coding sessions. Self-hosted backend support.

Semantic search over local files for pi. Indexes text/markdown, watches for changes, exposes a knowledge_search tool to the LLM.

Welcome to the LinkedIn Automate Comment project! 🚀🤖 This tool combines web scraping, sentiment analysis, and natural language processing 🧠✨ to automate meaningful LinkedIn interactions by generating and posting thoughtful comments 💬💡. Boost your engagement effortlessly! 🚀🔥

Benchmark test repo: Next.js project with intentional product-context gotchas for AI agent evaluation

Skills for AI agents to read web analytics like a senior analyst: diagnose traffic, judge channels, read funnels, declare typed events, and read A/B tests. Tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog.

AI-powered technical interview preparation platform with real-time voice conversations, live code execution sandbox, and comprehensive feedback. Built with LangGraph, LiveKit, FastAPI, and Next.js to simulate realistic interview scenarios with resume-tailored questions.

AI coding agent for your terminal. Reads, writes, edits code, runs commands. Any model. 14 kB.

Security scanner for AI agent skills and MCP tool bundles — prompt injection, IOC matching, malware detection, ML classifier

Deep research (CLI and agent skill) via the Gemini Interactions API. Automatic RAG grounding from local files (optional), cost estimation (--dry-run), adaptive polling, structured output, and agent onboarding. No Gemini CLI dependency. Universal AI agent skill for Claude Code, Amp, Codex, Clawdbot, and 30+ agents.

Bilibili MCP server (Model Context Protocol) for AI agents. Access user profiles, videos, dynamics, articles, subtitles, and followings.

Free, API-key-free MCP web search server — DuckDuckGo, Bing, Google + optional SerpAPI/Tavily. Works with Claude Desktop, Cursor, and any MCP client.

Load AGENTS.md into Claude Code sessions — no CLAUDE.md needed

AI-powered personal recommendation engine that learns preferences through pairwise comparison

Local-first AI Chief of Staff for engineering leaders

The CLI for MCP servers. Build and Install any server into VS Code, Cursor, or Claude Desktop in one command. Build and publish your own.

Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any MCP client.

91 production-proven patterns for building AI agents, extracted from a 512K-line codebase. Covers agentic loops, tool systems, permissions, MCP, prompt caching, multi-agent orchestration.

Hands-on beginner-friendly Generative AI projects covering Prompt Engineering, LLM APIs, Embeddings, RAG, Vector Databases, and AI Agents. Learn Gen AI by building real-world projects.

Local-first MCP memory server for AI coding agents with compact retrieval and project/global scopes.

Open-source API key firewall for AI agents. Proxy gateway with per-token rate limits, budget caps, model restrictions, and instant kill switch. Agents never see the real key.

418 AI agent skills across 31 domains & 54 roles. Role-based installer with export for Claude, ChatGPT, Gemini, Cursor, Copilot, Windsurf & any LLM API. Open source skill library that gives AI agents professional-grade methodology.

Docker image to run a self-hosted text embeddings and reranking server powered by Hugging Face TEI, with an OpenAI-compatible API. Supports BGE, Nomic, MiniLM and other models. Features optional reranking via cross-encoder models, API key auth, model management, offline/air-gapped mode, and persistent model cache.

Global quantitative stock analysis platform. Covers 35+ exchanges, provides technical indicators with automated risk management, and explains results in plain language using any LLM provider.

A customized Claude Code fork for routed models, multi-agent orchestration, and dense terminal control.

An open-source Digital Office of the CEO. Communications, scheduling, research, and knowledge work with governance-first architecture.

Creator operating system for AI-native workflows: skills, commands, agents, and plugins for Claude Code, Cursor, Windsurf, and Gemini.

Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session into a queryable, local SQLite record, then reads it back to predict your next dispatch, recall past incidents, attribute cost, and gate commits. The record is the product.

Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.

"Explore the cutting-edge Conversational AI project, leveraging advanced NLP & ML to create intelligent chatbots. Dive into code for natural language understanding, dialogue management, and dynamic response generation, designed for scalability and seamless integration across platforms."

Schuberg Philis collections of agents.md for guiding coding agents

Provide AI-driven penetration testing with portable hardware tools tailored for cybersecurity research and real-world testing scenarios.

MCP server for DataLikers — 29 Instagram & TikTok data tools. Thin stdio proxy. Use from Claude Code, Claude Desktop, Cursor, OpenAI Codex, Zed, Windsurf.

Free OpenAI-compatible LLM endpoint. Zero API keys, zero signup, zero user compute. Aggregates keyless public endpoints (Pollinations, ApiAirforce) with auto-failover, client-side queueing, and ad/notice filtering.

Cross-platform desktop app for switching Codex accounts and OpenAI API profiles on Windows, macOS, and Linux.

Context-aware caching proxy for Anthropic and OpenAI — maximizes prompt-cache hit rates by anchoring long-lived context into stable boundaries. Drop-in for Claude Code, Codex, Cursor, and custom harnesses.

🎨 Extract complete design systems from websites and generate AI-ready skill.md files to replicate exact design elements efficiently.

A Claude skill for rigorously solving math problems — equations, proofs, optimization, geometry, and more, with step-by-step reasoning and verification.

Privacy first toolkit for analyzing your ChatGPT and Claude exports. Model tracking, prompt effectiveness analysis, cost efficiency metrics (POD/DLOD/POE), topic classification, and industry benchmarks. 49 tests. pip installable. Everything runs locally.

Pure Go PDF library for reading & writing PDF (Go 1.20+): xref & streams, catalog/pages, text extraction, PdfWriter merge & forms—stdlib-only at runtime, ISO 32000–oriented API.

Obsidian community plugin: your vault as a private, self-hosted NotebookLM alternative. A built-in manager downloads and runs local AI models in one click, or use your Ollama and LM Studio. Cited answers from notes, PDFs, and code. Crawl websites into your library.

AI agent skills for resume building, job search, and career development. ATS checker, interview coach, cover letter writer, salary negotiation, and more. Works with Claude Code, Cursor, Windsurf, Codex, Gemini CLI

Generate advertising concepts, score them with industry criteria, and refine ideas using proven creative director methods.

A free, open-source browser-based AI agent platform; great for personal agents, professional work agents and small business owners. Agent teams ready. Local-first or deployed. Odoo, Quickbooks Online, Google Workspace and BambooHR connection built in. Agent curated CRM system included.

LLM multi-agent quantitative trading system for US equities. 9 specialized agents (8 daily + 1 quarterly meta-reflector) with schema-enforced reasoning chains, deterministic Python risk filters, real Alpaca integration, and quarterly self-evolution under a 10-invariant safety system.

Multi-agent platform using OSINT tools to create geopolitical analysis

AI personal assistant inspired by Iron Man's JARVIS — voice streaming, camera vision, Telegram bridge, browser control, file manager, flight finder, clap detection, game updater & more.

Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks

AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.

🛠️ Manage Home Assistant effortlessly with Claude for streamlined configuration, remote access, and custom dashboard creation.

Turns grant solicitations and draft proposals into a bid/no-bid memo, reviewer queue, evidence-gap list, and editable DOCX/XLSX package. Hosted demo, HTTP, and MCP.

台灣版 Claude for Legal：支援台灣民法自動更新、合約審查與法律實務 Playbook。基於 anthropics/claude-for-legal 擴充。

Official Anthropic Agent Skills — frontend-design, claude-api, docx, pptx, xlsx, pdf, canvas-design, mcp-builder and more