agent-swarm and swarm-tools

These two tools appear to be competitors, as both aim to provide frameworks for multi-agent swarm coordination, with "desplega-ai/agent-swarm" focusing on AI coding agents and "joelhooks/swarm-tools" targeting OpenCode with learning capabilities and agent management.

agent-swarm
51
Established
swarm-tools
40
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 15/25
Maintenance 10/25
Adoption 10/25
Maturity 5/25
Community 15/25
Stars: 250
Forks: 25
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 560
Forks: 44
Downloads:
Commits (30d): 0
Language: TypeScript
License:
No Package No Dependents
No License No Package No Dependents

About agent-swarm

desplega-ai/agent-swarm

Agent Swarm framework for AI coding agents and more!

Enables multi-agent coordination with a lead agent delegating work to isolated Docker-based workers, featuring real-time task tracking, persistent learning across sessions, and integrations with Slack, GitHub, GitLab, and email. The architecture uses an MCP API server as the central hub with SQLite persistence, supports scheduled workflows, skill management, and MCP server registration. Workers can expose HTTP services for inter-agent communication, and the system includes human-in-the-loop approval nodes and context usage monitoring across the swarm.

About swarm-tools

joelhooks/swarm-tools

🐝 Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management

Decomposes tasks into parallel subtasks with file-level locking via Swarm Mail to prevent conflicts, while persisting all coordination state through an event-sourced SQLite log and git-backed Hive tracker. Learns from past executions using semantic embeddings (Ollama-backed) to refine task decomposition strategies and flag anti-patterns when failure rates exceed thresholds. Runs entirely locally as an OpenCode/Claude Code plugin with no external servers.

Scores updated daily from GitHub, PyPI, and npm data. How scores work