GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
Python27,905 starslast pushed 3 hours agosemantica-agi
Graph-Native Infrastructure for Context and Accountable AI Systems
Python12,621 starslast pushed 9 hours agoopen-multi-agent
TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.
TypeScript6,904 starslast pushed 2 days agoiflytek
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
Java5,080 starslast pushed 59 minutes agoDrHazemAli
A source-grounded course and architectural reference for engineers designing systems that must survive real traffic, partial failure, security review, and changing requirements, spanning enterprise system design, distributed systems, AI systems, cybersecurity, reliability, cloud, HPC, edge, and mission-critical infrastructure.
—596 starslast pushed 3 weeks agodecionis
Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.
TypeScript532 starslast pushed 7 hours agocaipe-io
CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.
TypeScript407 starslast pushed 5 hours agofinewood2008
半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.
TypeScript104 starslast pushed 3 months agoAtomburstofficial
A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine
JavaScript104 starslast pushed 16 hours agodavidahmann
The Applied AI and FDE Guide: fieldwork, value engineering, and operations for agents that work beyond the demo.
JavaScript103 starslast pushed 6 days ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | mlflow The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data. | Python | 27,905 | last pushed 3 hours ago | |
| 2 | semantica-agi Graph-Native Infrastructure for Context and Accountable AI Systems | Python | 12,621 | last pushed 9 hours ago | |
| 3 | open-multi-agent TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included. | TypeScript | 6,904 | last pushed 2 days ago | |
| 4 | iflytek Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes. | Java | 5,080 | last pushed 59 minutes ago | |
| 5 | DrHazemAli A source-grounded course and architectural reference for engineers designing systems that must survive real traffic, partial failure, security review, and changing requirements, spanning enterprise system design, distributed systems, AI systems, cybersecurity, reliability, cloud, HPC, edge, and mission-critical infrastructure. | — | 596 | last pushed 3 weeks ago | |
| 6 | decionis Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant. | TypeScript | 532 | last pushed 7 hours ago | |
| 7 | caipe-io CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond. | TypeScript | 407 | last pushed 5 hours ago | |
| 8 | finewood2008 半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees. | TypeScript | 104 | last pushed 3 months ago | |
| 9 | Atomburstofficial A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine | JavaScript | 104 | last pushed 16 hours ago | |
| 10 | davidahmann The Applied AI and FDE Guide: fieldwork, value engineering, and operations for agents that work beyond the demo. | JavaScript | 103 | — | last pushed 6 days ago |
All · 11,658