Zero-overhead MCP proxy for AI coding agents — transparent wrapper gives subagents MCP access without loading schemas into the main context
DeepSeek Harness(DSH)一站式增强套件,基于公开插件扩展点构建,无需修改 DSH Core。提供 Windows Launcher、桌面通知与动态桌宠、Plugin Community、MCP Server Manager、模型输入类型配置、最后一条消息编辑与重新生成,以及 Claude Code / Codex Subagents 实时控制。所有功能均可独立安装,支持全量部署、
AI-Atelier, the all in one personal "atelier" (means handcraft studio in french) that can adapt to your need.
Multi-instance Claude Code manager with a bundled web UI for orchestrating multiple Claude Code agents from one place.
Dynamic Intelligence Graph (DIG) MCP server for AI coding agents. Persistent code knowledge graph, a code RAG improvement, with hybrid Graph + Vector + BM25 retrieval, agent memory, multi-agent coordi
Graph-native memory and self-learning for Claude Code. Every session remembered, every pattern learned, every agent connected — powered by AI Native Lang.
LangChain + LangGraph client using tools from a MCP server
MCP server + Claude Code plugin: multi-agent advisory squad with PRD-decomposed tasks, persistent learnings, weighted rubric scorecard, and PR posting.
Rust AI agent framework and self-hosted web console with MCP, Skills, sandboxed execution, persistent sessions, tracing, and file delivery.
MCP server for LangChain, LangGraph & DeepAgents knowledge + LangGraph agent debugging (Polly-like)
Multi-model deliberation as an MCP tool: several LLMs debate a question across rounds, then a chair synthesises consensus. Works with any OpenAI- or Anthropic-compatible provider.
Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.
A high-performance PostgreSQL-backed MCP server acting as a super memory, task tracker, and dynamic database manager for AI agents. Features built-in connection pooling, a professional tasks schema
Agent Personas as MCP Server — 16 tools, 13 personas (8 free: CEO, CFO, CTO, CMO, PM, Analyst, Support, Creative Director + 5 Pro specialists), 3 multi-persona workflows plus councils + ensembles. Zer
Zero-dependency .NET implementation of the Open Knowledge Format (OKF) v0.2: knowledge bundles as directories of markdown files with YAML frontmatter. Library, CLI validator, static site renderer, Age
Autonomous perp-trading agents on Hyperliquid with hard risk limits enforced in code, a tamper-evident public journal, paper + live modes, and an MCP server.
The open-source, video-first social platform for AI agents. Upload videos, live stream, DM, import TikTok, 27 MCP tools, trust scoring, webhooks. The only video platform in the AI agent ecosystem.
AI-powered agentic platform and Model Context Protocol (MCP) server for hybrid network automation and management. Unifies Cisco Packet Tracer, GNS3, SSH, Telnet, and physical hardware with multi-agent
Run a crew of coding agents across all your machines. One manager session hands out tasks; workers running Claude Code, Codex, opencode or any agent CLI take them, each in its own clone, and push a br
麦门圆桌(mcd-roundtable)|五个 AI 人格辩论,逼出最优麦当劳订单。基于麦当劳 MCP(mcd-mcp / Model Context Protocol)的多智能体点餐决策 Skill:菜单、券、营养、价格全部来自官方接口,金额只认 calculate-price,绝不估算。凑单最省 / 优惠券最大化 / 营养配餐 / 一键下单。Multi-agent McDonald's MCP
A production‑ready template for deploying multiple specialized medical agents as MCP tools using the AOP (Agent Orchestration Protocol) from the `swarms` library. This server exposes agents as callabl
Local coordination for parallel coding agents: scoped claims, isolated Git worktrees, shared resources and verified integration. MCP + VS Code/Cursor extensions. No hosted service.
The Declaration of Intelligence — signed in public, by pull request. https://thedeclaration.ai
Production-grade agentic RAG system built from scratch. LangGraph multi-agent orchestration, MCP, enterprise middleware, and RAGAS evaluation, with real production bugs diagnosed and fixed along the w
The tower of guard for parallel coding agents. Keeps parallel coding agents from stepping on each other. Claims, contracts and change notices over MCP.
Multi-agent Playwright MCP server with tab group isolation — multiple AI agents share one Chrome browser
The self-hosted bureau for AI agents: they get briefed on missions from a durable task queue, file what they learn into a markdown+git brain, and show up for work in a 8-bit Gameboy inspired office.
Long-term memory your AI coding agents actually share. One brain, many agents — standalone embedded MCP server: SQLite + FTS5 + vector hybrid search, local ONNX embeddings, self-expiring diary. No ser
Local CLI and daemon for supervising collaboration between Claude Code, Codex, Grok, Gemini, and other AI coding agents over MCP. Supports work directory sandboxing preventing unexpected writes by rev
Your coding agents as one team: Claude Code, Codex, opencode, Antigravity and Muse message each other, delegate subagents and share history, with a local dashboard and paired PCs.
One shared Markdown file that AI agents take turns writing to — context, decisions and progress all live in the file, so any agent can pick up the work without you summarising the last chat. Single bi
Where specs become law. One command turns any repo into a spec-driven, agent-ready project: Foundation (laws + gates), Compass (local code graph), Lawbook (spec workflow, ceremony 0–3) and Cortex (mul
Rust-core agentic framework with durable journal, exactly-once replay, Ed25519 A2A identity, and MCP tool server. Bindings for Go, Python, TypeScript, .NET, and Java via C ABI.
Your AI coding agent says the tests pass. Mythify makes it prove it: executed verification, product plans with human gates, and memory that survives the session. Any model, zero dependencies.
Mount MCP servers as filesystems to access reads via standard file commands and perform writes through a CLI tool.
The management layer for AI agents
完整目錄
編排與多代理控制。共 806 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。