Danau5tin/multi-agent-coding-system

Health v2 · maintenance only

Adoption not part of the score

1438 stars · 187 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python multi-agent AI coding system where an orchestrator agent dispatches explorer and coder subagents with shared knowledge artifacts, ranking #13 on Stanford's TerminalBench leaderboard. It also supports RL training of agent models across distributed Docker environments.

Use cases

• automate coding tasks with multiple cooperating AI agents
• benchmark an AI agent on TerminalBench
• orchestrate explorer and coder subagents with shared context
• train a coding agent model with reinforcement learning
• delegate software implementation work to LLM agents
• run concurrent agent rollouts in Docker environments

When to choose

• you want a proven multi-agent coding pipeline with strong benchmark results
• you need orchestrator/subagent delegation with reusable knowledge artifacts
• you want to RL-train an agent model at scale with open training code

When to avoid

• you need a simple single-agent coding assistant with minimal setup
• you want a polished GUI product rather than a framework
• your project cannot use LLM API costs or GPU training infrastructure

Facets

framework · maturity active

agent-framework llm-inference llm-training developer-tools artificial-intelligence large-language-models developer-tools python cross-platform cli multi-agent orchestration terminal-bench coding-agents context-sharing reinforcement-learning ai-agents automation docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Danau5tin/multi-agent-coding-system")