Coordinate multiple agents or tasks.
🔬 Local SQLite-based AI research agent swarm with GOAP planning, multi-perspective analysis, long-horizon recursive framework, AgentDB self-learning, anti-hallucination controls, and MCP server. Goal-oriented with parallel execution. No cloud dependencie
Install Orchestrix multi-agent infrastructure into any project. One command: npx orchestrix install
Spec-driven software development with security-guided multi-agent orchestration. Terminal AI coding agent with a Sensei second opinion, a Checker, six Sec-Test security personas, a Business Agent for xlsx/docx/pptx/pdf deliverables, and free-model support
ZAgents — mint a custom AI agent gemini from any repo. Browser Studio + `npx zagents` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM.
Deterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi.
Cross-platform local Agent IM runtime for secure Agent-to-Agent communication and collaboration via MCP, CLI, HTTP, and Web UI.
Production-ready MCP server with complete agent integration, multi-transport support, and comprehensive development automation tools for AI-assisted workflows.
MCP server that delegates coding tasks to your locally installed Qwen Code CLI. Wraps the real binary instead of bundling its own copy of the agent, so it inherits your auth, models and MCP servers. Sessions survive restarts, calls are cancellable, and ea
Execution engine for GAFF workflows - executes intent graphs with memory-backed state management, parallel execution, and HITL support
Outcome-first local MCP control plane for durable coding-agent investigation, implementation, review, and advice.
Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.
Local multi-agent squads for Claude Code, Codex, ZCode, Kimi Code and any MCP host
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
API-first MCP server for multi-model cross-review with unanimous convergence gates.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Provider-agnostic Model Context Protocol (MCP) collaboration server: claim files, persist working memory, and prevent multi-agent session conflicts
Run taskflow on Claude Code: the npm tarball provides the Claude subagent runner and MCP server; the plugin is distributed through the repository marketplace.
Production MCP server for secure access to Simplr integrations.
MCP server for parallel coding agents: detects file contention, coordinates claims, and prevents conflicts between agents working in the same repository.
Interactive CLI runner for H0wZy/mcp — The Ultimate Multi-Agent MCP Hub