GitHub repo leaderboard by stars, growth rate and activity.
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step.
AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
The platform for LLM evaluations and AI agent testing
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | 🦍 The API and AI Gateway | Lua | 44,115 | last pushed 4 days ago | |
| 2 | Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. | Python | 12,526 | last pushed 3 days ago | |
| 3 | Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents. | Java | 8,968 | last pushed Yesterday | |
| 4 | Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step. | Python | 6,589 | last pushed 1 month ago | |
| 5 | AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently. | TypeScript | 5,064 | last pushed 2 days ago | |
| 6 | RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry | Python | 4,418 | last pushed 6 months ago | |
| 7 | The platform for LLM evaluations and AI agent testing | TypeScript | 3,530 | last pushed 24 hours ago | |
| 8 | The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications. | Python | 1,103 | last pushed 1 week ago |
All · 11,474