Havuz

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.

A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows,

Open, self-hostable organization-of-record for AI agents — the accountable layer above any framework. Autonomy is earned, not assumed.

A general-purpose terminal AI agent with traceable knowledge sharing and dispute resolution｜面向终端的通用 AI 助手，可独立运行或参与团队协作，让 Agent 共享可检索、可追溯的知识，

Sandboxed Python environments with the uv workflow. Registry-only installs, read-only dependencies, and deny-by-default networking. Local-fi

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware

Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a

A2A protocol wrappers that turn AI backends into interoperable agents. Drop a JSON config, get a spec-compliant A2A server. Supports GitHub

the best free ai

The open infrastructure standard and reference implementation for AI agent cooperation, discovery, and marketplace.

Dissenyador visual de workflows i graphs d’IA agentiva · Diseñador visual de workflows y graphs de IA agéntica · Visual designer for agentic

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

HYBRO Hub: local & remote AI agents — private, powerful, unified.

Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an

Refactored fork of the sourcemap-leaked Claude Code CLI

Treat many repos as mono repos. Provide easy, scoped context to your agents. Use in parallel.

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

Lightweight multi-agent trading analysis framework with A-share, HK, and US market support

Fork decisions into living simulations with 1,000 personalities. Watch alternate realities diverge and explore second-order effects.

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

Local-first, model-agnostic LLM agent-harness research. Restart planned after a hiatus; existing code and historical claims await revalidati

An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orche

Local-first runtime for observable, debuggable AI-agent workflows with slidable autonomy and multi-agent/tool orchestration.

Structured project workflows for Claude Code. Published v1.5.1: 54 skill manuals / 8 departments. Development source: 64 / 9, with peer CEO,

Local Sovereign Multi-Agent Swarm OS & Cockpit for Autonomous AI Coding Agents. 28 Personas, 45 Core MCP Tools, Sub-10ms Trigram Search, Zer

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Markdown-first, human-gated multi-agent editorial workflow with explicit research, planning, writing, and review artifacts.

20 runnable LLM agent design patterns in Python, benchmarked, traced, offline-compatible. ReAct, multi-agent, constitutional AI, and more.

The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the trut

An autonomous multi-agent AI workspace that automates job hunting. Features native PDF parsing, ATS scoring, multi-engine job scraping, Play

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

Open-source agentic AI operating layer for hospital operations — multi-agent orchestration over FHIR-connected HIS data, built on LangGraph

ThorOS - a voice-controlled, AI-first Linux distribution built on Debian 13. Say what you want; on-device AI plans it and permissioned agent

Beginner-friendly Sol-led orchestration for Codex with pinned Luna and Terra workers and verified review.

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability gra

中文公司调研 Agent

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against

Multi-agent engineering with cold review, artifact validation and resumable run state.

Where AI agents hash it out 🤝 A self-hosted, peer-to-peer HTTP bridge that lets agents (Claude, GPT, local models) talk, coordinate, and deb

A tiny C runtime for durable AI agents: local-first, event-driven, restart-safe, and fully inspectable.

AI negotiation simulator powered by PPO reinforcement learning and LLMs. Practice salary, freelance, rent, and equity negotiations against a