Multi-Agent Systems
Multi-agent systems coordinate multiple autonomous or semi-autonomous agents to solve tasks through cooperation, communication, or division of work. Agents may specialize in different roles, share information, review one another’s output, or operate in parallel. This approach can help address problems that are too complex, broad, or time-consuming for a single agent, while introducing challenges such as coordination overhead, conflicting results, and error propagation.
Open source tools in this area include agent orchestration frameworks, communication and simulation environments, workflow libraries, and examples for building collaborative systems. When choosing one, consider its maturity, license, maintenance activity, supported models and languages, deployment requirements, and integration with existing tools. These resources are useful to developers, researchers, and teams exploring collaborative AI workflows, from controlled experiments to practical applications.
32 repositories · updated October 15, 2026
omnigent: Orchestrate AI Coding Agents Across Harnesses
Omnigent provides a shared orchestration layer for AI coding agents, with policies, sandboxing, and team collaboration. It suits developers who want to combine agent runtimes and access sessions across devices without tying workflows to one harness.
NewHealth 84/100
prime-agent: Run Self-Improving Agents for Coding Work
Prime Agent is a coding and research agent built for long-running tasks, using a persistent Python environment, recursive subagents, and durable working context. It suits developers and researchers who need agents to keep working across sessions.
NewHealth 82/100
AutoResearch: Turn Research Ideas into Reviewable Evidence
AutoResearch is a Python agent workflow for developing AI and machine learning research ideas into experiments and reviewable evidence. It suits researchers who want a traceable, resumable process and can configure model services and experiment resources.
NewHealth 42/100
atlas: Coordinate Coding Agents and Track Their Changes
Atlas is a desktop workspace for running multiple coding agents against one codebase and connecting their work to Git commits. It captures sessions and shares project context so teams and individuals can recover why a change was made and switch agents without restarting from scratch.
NewHealth 78/100
context-engineering-kit: Improve AI Coding Agent Workflows
A collection of installable skills, commands, and agents for improving coding-agent reliability and code quality. Use it to add reflection, specification-driven development, multi-agent workflows, and code review to supported AI coding tools.
ActiveHealth 46/100
agent-governance-toolkit: Govern Autonomous AI Agent Actions
Microsoft’s Agent Governance Toolkit adds policy checks, identity, audit logging, sandboxing, and reliability controls around autonomous agents. It suits teams integrating agent frameworks that need application-level enforcement and evidence of tool-call decisions.
ActiveHealth 80/100
ouroboros: Run a Persistent, Self-Modifying AI Agent
Ouroboros is a Python AI agent for desktop or headless use, designed to retain identity and memory across tasks and restarts. It can work in external projects, coordinate specialist agents, and evolve its own implementation through reviewed changes.
ActiveHealth 75/100
cli-agent-orchestrator: Coordinate AI Coding Agents
CLI Agent Orchestrator runs AI coding CLIs in isolated tmux sessions and gives a supervisor tools to delegate work to specialist agents. It suits developers who want to coordinate parallel or sequential coding tasks while keeping each agent’s native CLI.
ActiveHealth 75/100
awesome-ai-agents: Discover AI Agent Tools and Research
A community-curated directory of AI agent frameworks, platforms, infrastructure, evaluation tools, safety resources, papers, and learning materials. Use it to survey the ecosystem and find options for a particular agent-building need.
ActiveHealth 51/100
graphbit: Build Type-Safe Multi-Agent AI Workflows
GraphBit is a Rust-core framework with a Python API for building and running multi-agent AI workflows. It suits teams that need concurrent execution, multiple LLM providers, and workflow reliability with Python ergonomics.
QuietHealth 46/100
ruflo: Coordinate AI Agents and Autonomous Workflows
Ruflo is a TypeScript agent harness for Claude Code and Codex. It adds coordinated agent teams, persistent memory, workflow automation, and MCP integrations for developers building multi-agent systems.
ActiveHealth 73/100
clowder-ai: Coordinate AI Agents as a Collaborative Team
Clowder AI adds a platform layer for coordinating agent CLIs from multiple model families. It is for developers who want agents to retain roles and shared memory, communicate with one another, and review each other’s work.
ActiveHealth 70/100