Context-aware agent orchestration. Open source, Apache-2.0.
3-way operational transform / conflict resolution merger for multi-agent concurrent writes to code/documents with rollback journals
Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.
Terminal UI for BoJ local-coord-mcp — peer discovery, task coordination, and window titling for multi-instance AI sessions
本地 MCP 服务:让你正在用的 Agent 当 boss,把活派给本机的 Claude Code、Codex、Grok、DeepSeek、Devin 等 CLI 员工,单独派活或开会协作;托盘 App 是一间看得见、听得到的小办公室。Local MCP server: the Agent you already use becomes the boss and hands work to Cla
An MCP (Model Context Protocol) server that lets Claude/Codex/Cursor drive an OpenCode instance and delegate work to its subagents — so orchestrator models like Opus/Fable/GPT Sol, Astra can hand off
Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).
Unified Workspace with Multi Agent memory - Slipstream - 5-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, GUI, DXT-MCP Cloak Tools.
One Rust binary that runs sandboxed AI coding agents on Linux under a budget, in two modes: swarm mode runs 1 to 30 Pi agents on one goal, and agent mode is an always-on agent that takes requests from
Hand-offs for AI coding agents (Claude Code, Codex, Cursor, any MCP client): a hand-off is refused while a question to that agent is still open. Plain files in git, no server.
ClawSportBot Agent Network Protocol — the directory of the OddsFlow network's sports AI agents (football + Hong Kong racing, more planned), the open verification spec, and the live public prediction r
A security graph reporting tool, with agentic workflows, AI chat assistant, and automation for CVE remediation and graph data population.
Model and reasoning recommendations for subagents, powered by the OpenAI Decisions API.
A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Antigravity/Gemini)
MCP server for AI coding assistants: a curated knowledge base of engineering doctrine (kb_), live codebase exploration (code_), and verified learned memory (skill_*) — plus slash commands that carry w
KhaosMCP is a local-first, agent-operated pentest platform using AI via MCP. It connects the external operator to the complete assessment cycle: scoping, supervised execution, integrations, evidence g
Chat between the AI agents on your machine — they coordinate, ask each other questions, and get notified. No server to run.
Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.
Have an LLM (LangGraph agent) control QuantLib, the cache, your databases and any plug-in tools. Includes evaluator framework and an Excel/LibreOffice API in https://github.com/FulgentMcGuffin/cqfi-xl
MCP server + Claude Code plugin: multi-agent advisory squad with PRD-decomposed tasks, persistent learnings, weighted rubric scorecard, and PR posting.
MCP bridge connecting Claude Desktop, Claude Code CLI, and Chrome Extension. Skills, hooks, autonomous dev loops, and inter-agent communication.
Local MCP orchestrator for supervising Codex, Claude, Cursor, and OpenCode worker runs.
One home for every AI agent. Build, test and ship agents once, then use them from Claude, ChatGPT, Codex, Cursor, VS Code or Slack (MCP, OpenAI-compatible, A2A, ACP). Self-hosted, with teams, approval
A coherence control plane for multi-agent systems: one versioned source of truth for your system's mission and principles, served over MCP.
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.
Open-source mission control for AI agent fleets — chat to provision, agents to operate, humans to approve.
Vendor-neutral graph orchestration for reliable agentic systems: one portable Graph IR, native TypeScript/Python runtimes, deterministic barriers/routers, and cross-language conformance.
Manusclaw: Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks — across 12+ messaging channels, with voice wake, live canvas, SSH control, and multi-agent routing. No
The wallet your AI agent can't drain. A non-custodial Soroban treasury that bounds what an autonomous agent may spend - enforced by the contract, not the model.
Android MCP for AI agents: 66 tools, independent app sessions, branching on-device plans, PNG/MP4 capture, files, notifications and bounded ad-control jobs. Self-hosted with Shizuku.
A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control
Executed-evidence verification gate for AI coding agents
MCP server for the X (Twitter) API — with built-in safety rails for autonomous operation.
MCP server for the Paperclip AI agent orchestration API
Python CLI and library that splits a request across AI agents, runs the tasks on any model (Ollama, OpenAI-compatible, Anthropic), and keeps a hash-chained ledger you can verify and replay.
The tower of guard for parallel coding agents. Keeps parallel coding agents from stepping on each other. Claims, contracts and change notices over MCP.
完整目錄
編排與多代理控制。共 804 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。