Code agents

A Git intelligence MCP server built with Node.js and TypeScript that analyzes local Git repositories to surface insights like hotspots, churn, temporal coupling, knowledge maps, and risk scoring. Designed for AI agents, it exposes repository analytics tools through the Model Context Protocol (MCP) while keeping all data local and read-only.

ExcelFlow: AI-powered Excel assistant with natural language processing. Chat with your spreadsheets using OpenAI GPT-4o, perform operations, and get insights through a modern React + FastAPI web interface. Real-time updates via WebSockets.

Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.

Local-first, read-only MCP server to talk to your XP Investimentos portfolio through Claude Desktop. TypeScript + SQLite. Zero scraping, zero credentials.

Structured wrapper for autonomous AI coding with Claude Code. PRD-driven task planning, atomic verification, and bash loop execution.

A collection of mainly my own productivity plugins for Claude Code.

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

[ICML 2024] Official repository of ICML 2024 - RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Simple Golang RAG Server

One memory layer for every AI agent. Local-first, markdown source of truth, and CLI/HTTP/MCP native. Your agent forgot who you are. Again. Dory fixes that.

Offline local-first personal knowledge base with document upload, vector search, and Ollama-powered RAG chat.

A tool for converting HTML and RST docs into Markdown, and loading them into PostgreSQL.

Chrome extension to copy YouTube transcripts with AI-friendly features

Open Source Single Binary Authentication for the Agentic Era.

🔄 Ralph Wiggum iterative AI development loops for GitHub Copilot. Self-referential coding automation that keeps improving until done. Cross-platform Python tool.

The first 100% file-based Local-First AgenticAI dev "construction yard", with its own memory & context, planning, writing and reviewing your code in safe sandboxes on your own machine.

On-device AI agent engine for mobile apps — embedded Node.js worker with Claude LLM, file tools, code execution, git, and extensible MCP device tools

Teach your coding agent to prove its own work — evidence, not claims

📡 AI 公众号智能日报 — 从几十个号筛出每天值得读的几篇 · 8 渠道推送 · 12+ 模型

Stateful browser runtime for AI agents built on Playwright, with stealth interaction, structured page state, resilient automation, and debug observability.

Claude skill for building Claude skills. An interactive 9-step workflow distilled from Anthropic's complete guide — covering use cases, frontmatter, instructions, design patterns, testing, and distribution.

Package manager for AI coding assistants — manage skills, agents & MCPs across Claude Code, Codex, Copilot, and Cursor

Build real ML models without writing training code Upload your dataset + describe your goal → AI generates ready-to-train TensorFlow/Keras code + models — No ML experience required.

Spectrum: a deterministic semantic encoding enabling constant-time retrieval primitives

An AI-powered chatbot that answers student questions using university PDFs with the help of Google's Gemini API and RAG (Retrieval-Augmented Generation) architecture.

Simple, practical AI agent testing in TypeScript

Token-efficient log file system - improve memory, reduce AI context bloat

A collection of small hooks and extensions for the Pi coding agent

Automate Your GitHub Flows with MCP!

🤖🧠 Agentic development workflow for AI–HI (Human Intelligence) collaboration

A local desktop app for creating AI companions with unique personalities, emotional depth, and persistent memory.

Self-hosted personal finance and document workspace — multi-entity tax records, net worth across brokers/crypto/metals/real estate, Claude-parsed PDFs, Apple Health + DNA ingest, macro + crypto quant dashboards, and AI-generated strategy notes. One container, one volume, zero telemetry.

MCP сервер для интеграции с YouGile

Switch between Claude Code accounts instantly. Per-terminal isolation, API key fallback, auto-update.

Automated governance framework for Claude Code — multi-model council, WIP lifecycle hooks, company memory, and security gates

Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants

Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.

The web data layer for AI agents — fetch, search, crawl, extract, screenshot, and monitor the web with 50+ domain extractors and MCP.

AI-controlled browser farm on your machine. 37 MCP tools for Claude Code & Cursor — run N Chromium instances with device emulation, screenshots, network/geolocation simulation. Native GUI on Windows, Linux & macOS, plus a headless server for CI/CD.

Multi-model AI agent orchestrator. Run Claude, GPT, and Ollama agents in one workspace with group chat, smart routing, and per-agent model assignment.

Open-source AI Agent platform built on .NET — design, test, and deploy agent workflows

Learn Agentic AI with notes, resources, and practice code covering Generative AI basics, OpenAI agents SDK, prompt engineering, memory, model settings, design patterns and many more.

Sovereign AI orchestration engine with a learning Conductor. Routes between 400+ models across 15+ providers. Streams responses, detects refusals, learns from your patterns.

Curated papers, datasets, and benchmarks for social network simulation, from classical network models to LLM-based agentic social systems.

🚀 Comprehensive LangGraph learning repository with hands-on examples, and practical implementations. Master stateful multi-agent applications, RAG systems, SQL agents, custom tools, and debugging techniques. From basics to advanced workflows with real-world examples.

FastAPI-based boilerplate for building LangGraph-powered agents with streaming, observability, and modularity in mind.

A sample project for RAG with Node.js

A Model Context Protocol (MCP) server that provides programmatic access to Basecoat CSS components and their usage documentation. This server allows AI assistants to help developers build HTML interfaces using the Basecoat CSS framework.

Antigravity Architect is the definitive Agent-First project engine. It is a modular, zero-dependency Python package that generates Living Repositories—complete development environments designed from the ground up to be self-describing, self-protecting, and self-evolving for AI coding agents like Gemini, Claude, and GPT-4.

Skills I use and develop to deliver better outcomes faster and with less effort.

Open-source AI desktop assistant. Chat with multiple LLM providers (OpenAI, Claude, OpenRouter) in a native app with agentic tool use, MCP server support, and built-in file/shell tools.

📊 CLI tool to track Claude Code usage, costs & token consumption. Analyze your AI coding assistant spending locally.

A high-fidelity Perplexity AI clone built with React 19, TypeScript, and Tailwind CSS. Features a real-time RAG pipeline (SerpAPI + GLM-4.7-Flash), streaming responses, markdown rendering with syntax highlighting, and persistent chat history via Zustand.

ExaAiAgent — Advanced AI-powered penetration testing framework with Docker sandbox, multi-agent workflows, and 50+ integrated cybersecurity tools.

GitHub security posture analysis for AI agents — 39 MCP tools, 45 checks across org, repos, Actions, secrets, supply chain, and access control

加密货币 AI 自动交易与回测系统 · LangGraph 多代理辩论 + 硬性风控 + 决策日志 | AI-powered crypto trading & backtest with LangGraph multi-agent debate, hard risk controls, and Decision Journal

Security working agreements for AI coding agents: hardened AGENTS.md, prompt/tool-injection guardrails, dependency hygiene, Scorecard-ready OSS setup

Stop writing 200-line skills that Claude skims. Convert any skill into a gated micro-pipeline with hard YES/NO quality checks.

AI Company Orchestration Platform — Deploy governed teams of autonomous AI agents with Runtime Agentic IAM, credential vaults, heartbeat orchestration, and enterprise security. Built on Paperclip.

Make the leaked Claude Code runnable with unified local model support.

Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.

🚀 Access and install over 50,000 skills for AI agents with one command using the versatile agent-skills-cli tool.

TiyCode is an AI-first desktop coding agent. “钛可”是一款践行 AI First 理念的桌面版 Coding Agent

Two-pass code audit skill for Claude Code: adversarial Opus deep review + Codex second opinion

Zsh completion for the Claude Code CLI — completes the sessions, MCP servers, agents and models in your own configuration. 120+ languages.

Idiomatic Kotlin wrapper around com.anthropic:anthropic-java — suspend / Flow / sealed types over the official Anthropic Java SDK.

This is a multi-agent processing system with long-term and short-term memory+mcp+local tools+Agentic Rag. It uses the LLM locally deployed by ollma and PostgreSQL to store user's data, and the back-end uses grpc,gorm and gin to coordinate the output of the agent.

Autonomous AI agent for Home Assistant with multi-model routing, persistent memory, and an OpenAI-compatible API

Open-Source Prompt Injection Scanner for AI agents. 225 detection patterns across 17 categories, 15 languages. REST API, EU AI Act compliance mapping, <10ms latency.

Open-source AI agent: 11 LLM providers (OpenAI, Claude, Ollama, DeepSeek…), 60+ tools, web search, vision, browser & Android automation, MCP plugins, Second Brain memory — CLI · Telegram · WhatsApp · REST API

Event Horizon is a VS Code extension that visualizes AI coding agents as a living cosmic system. Instead of viewing logs, terminals, or raw agent output, developers observe agent behavior in real time through an interactive universe.

Open-source AI workforce platform. 55 tools, 21-page admin panel, multi-LLM (Claude/GPT/Gemini/Ollama), multi-PC deployment. Automates office tasks: Excel, email, CRM, invoicing, web research, and more.

Figma → Code (HTML/CSS/Tailwind/tokens), read by any AI agent via MCP. Free, local, no Dev seat, no account.

Self-hostable runtime for persistent autonomous coding agents — KVM-isolated VMs (or rootless containers), A2A-protocol executor with signed AgentCard discovery, AIWG mission dispatch, web dashboard, virtiofs shared storage. Runs on your hardware; no hosted control plane.

Complete Unity AR application for XREAL Air 2 smart glasses featuring a Jarvis-like AI voice assistant powered by OpenAI ChatGPT API with hands-free voice control, maps overlay, and real-time information display.

Cursor IDE 2.0 Complete Guide: AI-powered development with Composer, Debug Mode, Visual Editor, MCP, parallel agents. Learn TDD, refactoring, infrastructure-as-code patterns. 6-part comprehensive tutorial with 30+ recipes.

✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation

Tiny HTTP proxy that lets OpenClaw (and other third-party agents) route Anthropic /v1/messages through your claude login OAuth session. Avoids the third-party-app rejection, preserves tool-use bridging.

Model Context Protocol for Claude-Code and GoDot

Strip LLM writing patterns from prose, code comments, and commits — CLI, Claude Code skill, Cursor rule, and LLM system prompt.

Offline RAG-powered technical support agent for gas field engineers using Foundry Local, Phi-3.5 Mini, and SQLite vector store

Best Team for GitHub Copilot & Claude Code & Codex Workflow with Multi-Agent Collaboration, Long-Term Memory, and Self-Evolution.

Minimal Coding Agent for use on iPad/iOS in a-Shell Terminal

The composable agent development environment. Built in Zig. Modal. Extensible. Everything above the primitives is a plugin.

📰 OpenClaw Skill: Daily AI/Tech digest from 92 Karpathy-curated blogs. Zero deps, no API keys. Agent-native RSS → Score → Summarize pipeline.

FloatChat AI is a conversational AI platform for ARGO Ocean Data Discovery and Visualization, providing accurate and interactive tools to explore oceanographic data. Built with Python, LangChain, Pandas, and machine learning models, it makes complex ocean data accessible and actionable for researchers and enthusiasts.

Multi-agent orchestration plugin for Claude Code. Coordinate agent teams with shared tasks, messaging, and 7 patterns including RLM (arXiv:2512.24601) for large-file analysis beyond context limits.

An operating model for autonomous agent teams. Identity, task contracts, failure memory, trust scoring and audit for teams that want to operate agents as an accountable workforce.

Multi-Agent Comic Generator powered by the @google-gemini API. Turn simple prompts into comics with AI-generated stories, consistent characters, auto speech bubbles, and 7 language support. Built with FastAPI and deployed on Google Cloud Run.

Free, open-source Claude usage monitor for macOS & Raycast. Track token limits, burn rate, per-project costs, team budgets, and get alerts before you hit rate limits.

📝 Structured Prompt Skill - A Claude Code skill with 395+ AI prompt templates. Create professional AI prompts, personas & system prompts. | 结构化提示词技能 - 内置395+提示词模板的Claude Code技能

Self-hosted workbench host for AI coding agents. Each project gets a themed dashboard where the agent drops approval forms, runbooks, files, and review docs — out-of-band from chat, persistent, auditable. FastAPI + Svelte 5, single static binary or Docker, single-user.

Debugging-first MCP server for n8n. Tools for workflow generation, linting, per-node execution diagnosis, and driving live n8n instances. Built for AI agents.

Reuse your AI subscriptions. One module, every provider. OAuth PKCE for ChatGPT Plus/Pro, API keys for Claude/Gemini/DeepSeek, device code for Copilot. ~500 LOC, only depends on httpx.

The Agentic Development Environment You Need.

Secure email proxy for AI agents — content filtering, PII redaction, and prompt injection detection over MCP

Governed context for customer-facing agents. CRMy gives AI agents trusted customer context and action boundaries in one briefing_get call. MCP-native. PostgreSQL-backed. Open source.

MCP server for rclone.

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.

AI agent for Claude Code that tailors resumes to job descriptions with ATS optimization and LaTeX PDF output. Zero fabrication - every claim sourced from your career document.