Awesome AI Agents › Collaborative Swarm Systems
Swarm (package opencode-swarm-plugin) adds multi-agent coordination to the OpenCode and Claude Code coding agents, with the stated goal of surviving context loss between sessions. A single slash command takes a task description, decomposes it into parallelizable subtasks, creates tracking entries, spawns worker agents, coordinates them, reviews each completion before approval and records the outcome for future runs. Three components carry the state. The Hive is a git-backed task tracker stored in a .hive directory, so tasks persist across sessions and synchronize through the repository itself; tools create cells, list them by status and close them with a reason. Hivemind is a semantic memory layer built on embeddings where agents store learnings with tags and search them later by query. Swarm Mail is an actor-model coordination layer that lets agents reserve file paths exclusively so parallel workers do not conflict, send messages to each other and write checkpoints. Everything runs locally with no external servers: libSQL provides embedded SQLite for event sourcing, the Hive lives in git, and Hivemind uses Ollama for embeddings. Installation is a global npm install plus a setup command for OpenCode; for Claude Code the same CLI is installed and the repository is added as a plugin marketplace, after which the MCP server starts automatically. Alongside the main swarm command the plugin exposes commands to query and manage tasks, check an inbox of messages from other agents, inspect coordination status and end a session with sync and handoff notes. A small CLI covers setup, a doctor check for dependencies, initializing a hive in the current project and showing config paths. It targets developers already using agentic coding CLIs who want parallel workers under explicit coordination.
https://github.com/joelhooks/swarm-tools
AgentVerse is a versatile open-source framework that enables the deployment and collaboration of multiple LLM-based agents for task-solving and simulation applications, supporting research and development in multi-agent AI systems.
Solace Agent Mesh is an open-source event-driven framework for building and orchestrating scalable multi-agent AI systems that integrate with real-world data and systems.
Langroid is a Python framework that enables building LLM-powered applications using a multi-agent programming approach for collaborative problem solving and enhanced developer experience.
EvoAgentX is an automated framework for building a self-evolving ecosystem of AI agents that generate, evaluate, and execute multi-agent workflows based on natural language goals.
agentUniverse is a multi-agent framework based on large language models that enables developers to build collaborative intelligent agents integrating domain expertise for solving complex problems.
Public research log of Hyperspace, a libp2p peer-to-peer network where autonomous agents run experiments across five domains, gossip findings, pool machines into private pods and train models collaboratively.
GPTeam is an open-source multi-agent simulation platform that uses GPT-4 to enable AI agents to collaborate and communicate effectively to achieve predefined goals.
uAgents is a lightweight Python framework by Fetch.ai for creating secure, decentralized autonomous AI agents that operate within a blockchain-enabled network.