Havuz

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

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

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

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

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

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315

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

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

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

Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, a

Claude Code, Codex CLI, Gemini CLI ve diğer yapay zekâ destekli coding agent’larını tek merkezden yöneten açık kaynaklı bir multi-agent orch

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

Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim che

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

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first,

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

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

Runtime-adaptive steering layer and portable control contract for hard agentic work: durable goals, proportional control, bounded delegation

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

Retrieval-augmented generation: training-free document-assessment routing for cost-efficient multi-agent RAG.

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

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

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

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

Mantis, AI coding agents ile kod tabanlarındaki güvenlik açıklarını araştırma, yeniden üretme ve düzeltme iş akışları kurmaya yönelik modüler bir toolkit ve referans harness sunuyor.

Neden yükseliyor · AI agent’lar ile güvenlik açığı bulma ve düzeltme ilgisinin artması projeye görünürlük kazandırmış olabilir; ancak yalnızca verilen ölçümlerden yükselişin nedenini doğrulamak mümkün değil. 104 günlük yaşında 1717 yıldız dikkat çekici ilgi gösterse de son 28 gündeki 5 commit ve 1 farklı yazar, güncel geliştirme hareketliliğinin sınırlı olduğuna işaret ediyor.

AI Town Portable is a browser-based multi-agent simulation built on Generative Agents, with LLM-driven residents, long-term memory, planning

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

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

Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

Agentlas-OS, farklı agent host’larında uzman agent’ları bir hub üzerinden kullanıp görev başına geçici bir orchestrator oluşturan bir agent framework’üdür.

Neden yükseliyor · 116 günde 1540 yıldız ve son 28 günde 113 commit, projeye belirgin ilgi ve geliştirme hareketliliği olduğunu gösteriyor. Çok sayıda coding agent host’uyla çalışma ve uzman agent’ları bir araya getirme iddiası da güncel agent iş akışı arayışına hitap ediyor. Ancak son 28 gündeki 2 farklı yazar, hareketliliğin dar bir ekibe bağlı olduğunu gösteriyor; yıldızlar tek başına benimsenme kanıtı değil.

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

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

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

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

中文公司调研 Agent

Raven, farklı uzmanlaşmış agent'ları ortak bir iş akışında koordine eden ve çok adımlı görevler için DAG oluşturan bir multi-agent orchestration yazılımıdır.

Neden yükseliyor · 129 günlük yaşına karşılık 4.087 yıldız ve son 28 günde 16 farklı yazarın 938 commit'i belirgin ilgi ve aktif geliştirme gösteriyor. İlginin muhtemel nedeni, uzman agent'ları tek yüzeyde koordine etme ve harness'leri geliştirme iddiası; ancak yıldız ve commit sayıları tek başına benimseme ya da kalite kanıtı değil.

Universal AI Agent Swarm & MCP Plugin with 176 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf,

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

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

CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs

An agent that builds, plays, and verifies its own game ? a colony-sim prototype gated by 15-scenario input-level repro tests + isolated-grad

Cord — distributed agent fabric for LLMs, MCP servers and AI agents. Discover any LLM CLI / HTTP backend / MCP server across machines via na

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

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Connect agents across runtimes, frameworks, and teams.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named pattern

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