Coding Agents ListingsCoding Agents

Mycelium

🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

Windbg MCP

MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --listen

Agent Airlock

A type-checker and contract layer for AI agent tool calls: in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

MCP Manager

A cross-platform desktop app for managing MCP server configs across Claude Code, Codex, Cursor, VS Code, OpenCode, Gemini CLI, and more.

Cognirepo

Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce token usage.

Kafka MCP

MCP Server for Apache Kafka

Remote Workspace MCP

远端工作区 MCP 服务：为编码 Agent 提供类本地的文件读写、搜索、命令执行与传输同步能力。

Terminal MCP

An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.

Pulsechain MCP

PulseChain MCP server for AI agents: chain reads, markets, swap quotes, and encrypted wallets

AI Agent Guidebook

Comprehensive guides for AI coding assistants: Claude Code, GitHub Copilot, Gemini CLI. Includes MCP servers, multi-agent orchestration, and production templates.

Claude Code Antiregression Setup

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

Gyrfalcon

MCP-сервер для 1С:Предприятие (1C, BSL): навигация по коду, метаданные, граф вызовов. Детерминированный индекс вместо чтения выгрузки — один бинарь, без зависимостей и облака.

Awareness SDK

Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor, Windsurf, OpenClaw. Zero-code interceptors for OpenAI/Anthropic. Python & TypeScript SDKs.

Agent Debugger

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

MileStack

面向 Vibe Coding 项目，让开发者和编程 Agent 不必翻找零散文档和历史对话，也能随时掌握进展、接续工作并稳步推进。

MCP Persist

Production-grade persistence backends for the MCP Python SDK.

Python AI

Durable execution for AI agents in Python: make LangGraph, CrewAI, Pydantic AI, OpenAI Agents, Google ADK, Strands and more fault-tolerant with Dapr Workflows on Diagrid Catalyst. Crash-proof agents, no re-run LLM calls.

Lain

High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust.

Genpark Bidirectional Human Agent State Sync Coordinator Skill

CoAgents / CopilotKit bidirectional human-agent workspace state sync coordinator

Terminal MCP

Connect AI agents to ANY device, ANY protocol, ANY network. Every connection type in 1 unified tool: Serial ports, TCP, Telnet, WebSocket, SSH, Bluetooth (Classic & BLE), RFC2217, Unix sockets, named pipes, STDIO. Rich command sequences, atomic execution, logging, async ops, pattern matching, ANSI terminal emulation...Built for AI to get work done.

Admina

The open framework for governed AI development: EU AI Act compliance, PII redaction, MCP proxy, prompt-injection firewall. Python + Rust, Apache 2.0

Agentic Dns

POSIX-native MCP server for intercepting DNS escapes and enforcing deterministic domain resolution for autonomous agents.

Stateweave

git for agent brains — move, debug, and secure AI agent state across 10 frameworks

Diffchunk

MCP server for chunking and navigating large diff files in AI-assisted code review. Empowers your AI Code Reviewer to better work on large changes.