{"id":49953696,"url":"https://github.com/ry-ops/commit-relay","last_synced_at":"2026-05-17T21:20:04.182Z","repository":{"id":355778664,"uuid":"1175853301","full_name":"ry-ops/commit-relay","owner":"ry-ops","description":"Autonomous multi-agent AI platform for GitHub repository lifecycle management. MoE routing, self-healing workers, LLM mesh gateway, RAG-enhanced context, enterprise governance. [Archived]","archived":false,"fork":false,"pushed_at":"2026-04-27T10:45:03.000Z","size":5959,"stargazers_count":1,"open_issues_count":20,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-05T08:41:38.629Z","etag":null,"topics":["ai-agents","anthropic-claude","autonomous-agents","devops-automation","enterprise-governance","github-automation","llm","mcp-server","mixture-of-experts","multi-agent-system","nodejs","observability","opentelemetry","python","pytorch","rag","self-healing","typescript","vector-database"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ry-ops.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":"GOVERNANCE-ARCHITECTURE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-08T09:09:50.000Z","updated_at":"2026-03-09T23:23:14.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ry-ops/commit-relay","commit_stats":null,"previous_names":["ry-ops/commit-relay"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ry-ops/commit-relay","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry-ops%2Fcommit-relay","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry-ops%2Fcommit-relay/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry-ops%2Fcommit-relay/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry-ops%2Fcommit-relay/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ry-ops","download_url":"https://codeload.github.com/ry-ops/commit-relay/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ry-ops%2Fcommit-relay/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33155545,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-17T09:28:26.183Z","status":"ssl_error","status_checked_at":"2026-05-17T09:27:52.702Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","anthropic-claude","autonomous-agents","devops-automation","enterprise-governance","github-automation","llm","mcp-server","mixture-of-experts","multi-agent-system","nodejs","observability","opentelemetry","python","pytorch","rag","self-healing","typescript","vector-database"],"created_at":"2026-05-17T21:20:03.579Z","updated_at":"2026-05-17T21:20:04.175Z","avatar_url":"https://github.com/ry-ops.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"https://github.com/ry-ops/commit-relay/blob/main/commit-relay.png\" width=\"100%\"\u003e\n\n# Commit-Relay\n\n**Multi-agent AI system for autonomous GitHub repository management.**\n\n[![Status](https://img.shields.io/badge/Status-Archived-lightgrey)](https://github.com/ry-ops/commit-relay)\n[![Architecture](https://img.shields.io/badge/Architecture-Master--Worker-blue)](./docs/master-worker-architecture.md)\n[![License](https://img.shields.io/badge/License-MIT-yellow)](./LICENSE)\n\n\u003e **Note:** This project is archived and no longer in active development or production use. The codebase is preserved as-is for reference.\n\n---\n\n## What is Commit-Relay?\n\nCommit-Relay was an autonomous multi-agent platform that managed the entire GitHub repository lifecycle — from task routing to code implementation, security scanning, testing, and deployment — with zero manual intervention.\n\nAgents communicated through structured coordination files rather than direct API calls, creating a fully auditable, transparent orchestration system. A central Coordinator routed incoming tasks to specialized master agents using a Mixture of Experts (MoE) router, which then spawned lightweight workers to execute in parallel.\n\n---\n\n## Architecture\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./docs/architecture-overview.svg\" alt=\"Commit-Relay Architecture Overview\" width=\"100%\"\u003e\n\u003c/p\u003e\n\n### Core Components\n\n| Component | Description |\n|-----------|-------------|\n| **5 Master Agents** | Coordinator, Development, Security, Inventory, CI/CD |\n| **7 Worker Types** | Implementation, Fix, Test, Scan, Security Fix, Documentation, Analysis |\n| **8+ Autonomous Daemons** | Coordinator, Worker Manager, Process Monitor, Heartbeat, Zombie Cleanup, Worker Restart, Failure Detection, Auto-Fix |\n| **LLM Mesh Gateway** | Multi-provider support (Anthropic, OpenAI, Ollama) with circuit breakers, cost tracking, and automatic failover |\n| **MoE Router v4.0** | 350+ activation keywords, learned weights, semantic routing, 100% routing confidence |\n| **RAG System** | FAISS vector store with 5 collections (code, docs, decisions, patterns, tasks) using sentence-transformers |\n| **API Server** | 128 REST endpoints, WebSocket streaming, rate limiting, authentication |\n| **MCP Server** | Model Context Protocol interface exposing system capabilities as tools |\n| **Python SDK** | Full client library with task orchestration, analytics, health monitoring, and reporting |\n| **Observability** | Elastic APM, LangSmith tracing, 27 event types, distributed tracing, anomaly detection |\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./docs/system-components.svg\" alt=\"Commit-Relay System Components\" width=\"100%\"\u003e\n\u003c/p\u003e\n\n---\n\n## Key Capabilities\n\n### Intelligent Task Routing\n- Mixture of Experts router with 350+ keywords and continuous learning\n- PyTorch neural routing with training pipeline\n- Semantic routing via embeddings (94.5% coverage)\n- Margin-based confidence with automatic fallback\n\n### Self-Healing System\n- 12+ automated remediation strategies\n- Heartbeat monitoring with 2-minute intervals\n- Zombie worker detection and cleanup\n- Exponential backoff restart logic\n- ML-based failure pattern recognition\n\n### LLM Mesh (Multi-Provider Gateway)\n- Anthropic Claude (primary), OpenAI, and Ollama support\n- Cost-aware model selection (simple tasks -\u003e haiku, complex -\u003e opus)\n- Circuit breaker middleware with provider health monitoring\n- Automatic failover chains with retries\n- Token usage and cost analytics\n\n### Enterprise Governance\n- PII scanning (emails, phone numbers, SSNs, API keys)\n- RBAC with permission inheritance across 7 namespaces\n- SOC2, GDPR, HIPAA compliance policy checking\n- Data quality monitoring with schema validation\n- Complete audit trail via file-based coordination\n\n### Observability Stack\n- Elastic Cloud APM with custom spans and business metrics\n- LangSmith for LLM performance tracking\n- 27 event types with real-time streaming\n- Distributed tracing with waterfall visualization\n- 50+ system metrics with aggregation\n\n### RAG-Enhanced Context\n- Pluggable vector store (Weaviate, Qdrant, file-based)\n- Connectors for GitHub, Confluence, Slack\n- Hybrid search (BM25 + semantic with Reciprocal Rank Fusion)\n- 5 specialized collections with metadata schemas\n\n---\n\n## Project Structure\n\n```\ncommit-relay/\n├── agents/              # Agent configs, prompts, logs, worker outputs\n├── api-server/          # Express.js API server (128 endpoints)\n├── config/              # System configuration\n├── coordination/        # File-based coordination (task queue, worker pool, handoffs)\n│   ├── masters/         # Master agent configurations and libraries\n│   ├── governance/      # Governance policies and audit logs\n│   ├── catalog/         # Data and AI catalog\n│   └── observability/   # Event streams and metrics\n├── docs/                # 40+ documentation files\n├── examples/            # Usage examples\n├── lib/                 # Shared libraries\n│   ├── cache/           # Adaptive LRU cache\n│   ├── governance/      # PII scanner, access control, compliance\n│   ├── orchestration/   # Workflow engine, SLA monitor, rate limiter\n│   └── rag/             # Vector store, embeddings, connectors\n├── llm-mesh/            # Multi-provider LLM gateway\n├── mcp-server/          # Model Context Protocol server\n├── python-sdk/          # Python client library\n├── scripts/             # 117+ operational scripts\n├── security/            # Security scanning and CVE tracking\n└── testing/             # Test suites and test utilities\n```\n\n---\n\n## Tech Stack\n\n| Category | Technologies |\n|----------|-------------|\n| **Runtime** | Node.js 18+, Python 3.8+, Bash |\n| **AI/ML** | Anthropic Claude, OpenAI, Ollama, PyTorch, sentence-transformers, FAISS |\n| **API** | Express.js 5, WebSocket, JSON-RPC 2.0 (MCP) |\n| **Observability** | Elastic APM, LangSmith, OpenTelemetry |\n| **Security** | Helmet, express-rate-limit, JWT, PII scanning |\n| **Data** | FAISS, Weaviate, Qdrant, MiniSearch |\n| **Deployment** | Docker, systemd/launchd |\n\n---\n\n## License\n\n[MIT](./LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fry-ops%2Fcommit-relay","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fry-ops%2Fcommit-relay","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fry-ops%2Fcommit-relay/lists"}