Harness Fleet Engineering
14 resources · page 1 of 1
AgentScope
Creator not supplied; see original source.
AgentScope GitHub repo: framework for building and running observable multi-agent applications.
ChatDev
Creator not supplied; see original source.
OpenBMB ChatDev GitHub repo: LLM-powered multi-agent collaboration framework for software development.
Gas Town (Steve Yegge)
Creator not supplied; see original source.
Gas Town GitHub repo (Steve Yegge): multi-agent workspace manager for coding agents such as Claude Code.
cursor/plugins: pstack
Creator not supplied; see original source.
pstack directory in Cursor's plugins GitHub repo, which holds the Cursor plugin specification and official plugins.
Paperclip
Creator not supplied; see original source.
Paperclip GitHub repo: open-source app for managing teams of agents with approvals and cost controls.
AutoGen documentation
Creator not supplied; see original source.
AutoGen documentation: Microsoft's multi-agent conversation framework, now in maintenance mode.
CrewAI documentation
Creator not supplied; see original source.
CrewAI documentation: Python framework for building multi-agent crews, flows and tools.
Dify documentation
Creator not supplied; see original source.
Dify documentation: open-source platform for building LLM apps, knowledge pipelines and agent workflows, cloud or self-hosted.
LangGraph docs
Creator not supplied; see original source.
LangGraph overview documentation: library for building stateful, graph-based agent workflows in Python.
Don't Build Multi-Agents (Cognition)
Creator not supplied; see original source.
Cognition post by Walden Yan arguing for shared context and single-threaded agents over naive multi-agent designs.
Multi-Agents: What's Actually Working (Cognition)
Creator not supplied; see original source.
Cognition follow-up post on which multi-agent setups work in production and where single agents still fit.
How we built our multi-agent research system (Anthropic)
Creator not supplied; see original source.
Anthropic post on how it built Claude's multi-agent Research system with an orchestrator and subagents.
Refactoring Hermes with 1,393 agents
Creator not supplied; see original source.
Nous Research case study of Hermes Agent refactoring its own codebase with 1,393 subagents, with cost and results.
Durable AI (Temporal Documentation)
Creator not supplied; see original source.
Temporal documentation on durable execution for AI applications and agents that resume after crashes or timeouts.