Dicklesworthstone/claude_code_agent_farm

Orchestration framework for running 20+ Claude Code agents in parallel: automated bug fixing, best-practices sweeps, lock-based coordination, and real-time tmux monitoring

What it solves

Claude Code Agent Farm allows developers to scale codebase improvements by orchestrating multiple AI coding agents in parallel. It eliminates the bottleneck of manual, one-by-one bug fixing or refactoring by deploying a "farm" of agents to systematically tackle linting errors, type-check failures, or the implementation of architectural best practices across large projects.

How it works

The system uses a Python-based orchestrator to manage multiple tmux sessions, each running an instance of a coding agent CLI (primarily Claude Code).

  • Parallel Execution: It launches multiple agents (up to 50) in separate terminal panes.
  • Task Distribution: Depending on the workflow, it either splits a generated list of linter/type-checker problems into chunks for agents to fix or provides a best-practices guide for agents to implement systematically.
  • Coordination: For complex tasks, it uses a lock-based file system (/coordination/ directory) where agents claim specific files or features to prevent merge conflicts and duplicate work.
  • Monitoring: A real-time dashboard tracks agent health, context usage, and progress, with auto-recovery features to restart agents that crash or idle.

Who it’s for

Software engineers and team leads managing large codebases across various technology stacks (including Next.js, Python, Rust, Go, and Java) who want to automate tedious maintenance, bug fixing, and standardization tasks.

Highlights

  • Multi-Stack Support: Pre-configured for 34 different technology stacks with tailored prompts and best-practices guides.
  • Conflict Prevention: A sophisticated lock-based registry that allows agents to coordinate work without stepping on each other.
  • Automated Lifecycle: Handles everything from environment setup (via 24 installation scripts) to automatic context clearing and git commits.
  • Flexible CLI Integration: While optimized for Claude Code, it can be aliased to work with other interactive coding agent CLIs like OpenCode or OpenAI Codex.

Related

  • Project
    perplexityai/pplx-garden

    A collection of open-source inference technologies from Perplexity AI, featuring RDMA-based communication for LLMs, a CPU-optimized tokenizer, and a Metal-based inference server for Apple Silicon.

  • Project
    milisp/codexia

    A lightweight agent workstation and command center for Codex CLI, Claude Code, and ACP-compatible agents, featuring task scheduling and a unified project workspace.

  • Project
    feldroy/air

    A web framework built on FastAPI and HTMX, specifically designed with a fully typed API to be easily written and understood by AI coding assistants.

  • Project
    retentioneering/retentioneering-tools

    An open-source Python toolkit and MCP server for reproducible product analytics on clickstream and event log data, enabling deep behavioral analysis of user journeys.