#multi-agent Repositories
239 repositories total
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.
Agent skill + renderer: turn a single JSON config (or an Excalidraw file) into an animated architecture diagramโeither a terminal-style live panel or a pastel infographicโas an MP4 or looping web page. Animated architecture diagrams / animated agent architecture, optimized for X and Xiaohongshu.
OpenSwarm โ Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.
Autonomous development for real products. You set the standard. Declare your vision. Walk away. It builds.
OpenโWebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more.
More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.
An AI multi-agent tool that turns research papers into cited commercialization and technology-transfer assessments covering TRL, the patent landscape, markets, and risks. Built with CrewAI + FastAPI, with a reproducible benchmark.
EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/)
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
Build durable, autonomous, resilient, and observable AI agents with built-in workflow orchestration, security, statefulness, and telemetry.
A self-evolved, sovereign desktop AI agent built for real-world action โ beyond model wrappers and coding copilots. / A desktop AI agent that self-evolves through real-world practice.
AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.
An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
๐ ๏ธ The meta-harness for AI agents โ scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
๐ Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management
AI Werewolf game. You take one seat, and LLM players fill the rest. AI Werewolf.
Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows
Exploring white-box AGI architectures: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (conditional space + semantic spatiotemporal graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
DataBuff is an AI-native APM built on OpenTelemetry, with multi-agent troubleshooting out of the box.
Multi-model orchestration layer for Claude Code โ the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
๐ฆ Augur โ A local-first investment research memory system: independent analyses by 18 investor personas + weighted consensus, with time-aware evidence and reproducible runs. CLI / Dashboard / MCP. A local-first research memory system with 18 investor personas.
TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors, and self-building designs
Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-hosted alternative to Grok Bot, Claude Duet and OpenAI dots. Rust + React.
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Multi-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. Next.js + React
An open harness to simulate and deploy PX4/ArduPilot/Betaflight perception-based drone swarms with ROS2, YOLO, NVIDIA Jetson
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi
Stanford CS329Z Engineering AI Agents Chinese tutorial: an AI agent course for Python developers, with 19 lectures and 4 hands-on projects, covering LLMs, RAG, tool calling, memory, multi-agent systems, evaluation, and safety. Complete Markdown, online and offline HTML. Chinese course notes.
An evolving workflow ยท Continuously iterated and self-evolving, powered by AI employees in EvoFlowโs R&D department ยท AI agent employees. Official website: www.evovexai.com
OS-level autonomous AI agent with long-term memory, multi-agent coordination, Titan Chronos scheduler & Moltbot Social Core
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
A local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama
HunterCode ยท Community Edition ยท An open-source, local alternative to Tencent WorkBuddy Finance Edition ยท Multi-agent investment research terminal for A-shares/Hong Kong stocks/U.S. stocks ยท Inference runs on your machine ยท Your positions never leave your hard drive ยท BYOK ยท Apache 2.0 ยท Self-hosted with Docker Compose
Run Claude Code, Codex, Antigravity, Grok Build, and OpenCode behind a single runtime, and count a run as complete only when the checks it didnโt write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.
mu (ฮผ): most of what a coding agent decides isnโt code. mu hands 40 kinds of yes/no decisions to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.