GitHub repo leaderboard by stars, growth rate and activity.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
Install, run and deploy your own decentralized AI agent service
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.
Optimizing inference proxy for LLMs
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. | TypeScript | 155,280 | last pushed 21 hours ago | |
| 2 | An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. | Python | 82,152 | last pushed 2 days ago | |
| 3 | 🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated | TypeScript | 71,836 | last pushed 21 hours ago | |
| 4 | Pocket Flow: 100-line LLM framework. Let Agents build Agents! | Python | 11,155 | last pushed 2 months ago | |
| 5 | The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents. | TypeScript | 10,598 | last pushed Yesterday | |
| 6 | Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes. | Python | 5,859 | last pushed 21 hours ago | |
| 7 | Install, run and deploy your own decentralized AI agent service | Shell | 5,019 | last pushed 11 months ago | |
| 8 | Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai | TypeScript | 4,956 | last pushed 6 months ago | |
| 9 | An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows. | Python | 4,933 | last pushed Yesterday | |
| 10 | Optimizing inference proxy for LLMs | Python | 4,262 | last pushed 2 months ago |
All · 11,474