{"adoption": {"forks": 187, "observed_at": "2026-08-28T04:04:43.885002+00:00", "stars": 1438}, "canonical_url": "https://ross.abutalabs.com/products/multi-agent-coding-system", "card": {"archived": false, "artifact_type": "framework", "description": "Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.", "domain": ["artificial-intelligence", "large-language-models", "developer-tools"], "enriched": true, "function": ["agent-framework", "llm-inference", "llm-training", "developer-tools"], "health_score": 64, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Danau5tin/multi-agent-coding-system"], "name": "Danau5tin/multi-agent-coding-system", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2025-11-03T12:22:00+00:00", "repo": "Danau5tin/multi-agent-coding-system", "stars": 1438, "tags": ["multi-agent", "orchestration", "terminal-bench", "coding-agents", "context-sharing", "reinforcement-learning", "ai-agents", "automation", "docker"], "topics": [], "urls": [], "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"], "what_it_is": "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/multi-agent-coding-system", "repo": "Danau5tin/multi-agent-coding-system", "role": "main", "score": 33}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.885002+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:38.383338+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d2e15a97a7ecca7dad01bb289ae73e7d02fbbffceceb61e72f0a88248fb56fd8", "fetched_at": "2026-08-28T04:04:43.885002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Danau5tin/multi-agent-coding-system"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 50, "longevity": 26, "rhythm": 14}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 368, "days_push": 303, "days_rel": 362, "gap_med": null, "n_releases_24m": 1}, "score": 33, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}