GitHub repo leaderboard by stars, growth rate and activity.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
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.
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).
A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense of control.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps | Python | 47,906 | — | last pushed 2 days ago |
| 2 | ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. | Python | 9,057 | — | last pushed 2 days ago |
| 3 | 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 | 6,894 | — | last pushed 2 days ago |
| 4 | Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support. | Python | 5,617 | — | last pushed 3 days ago |
| 5 | Harness LLMs with Multi-Agent Programming | Python | 4,101 | — | last pushed 6 days ago |
| 6 | The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider. | Python | 3,707 | — | last pushed 2 days ago |
| 7 | Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local). | TypeScript | 3,561 | — | last pushed 2 weeks ago |
| 8 | A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally | — | 2,835 | — | last pushed 2 days ago |
| 9 | Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp. | TypeScript | 2,515 | — | last pushed 2 days ago |
| 10 | open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense of control. | Go | 1,284 | — | last pushed 2 days ago |
All · 11,474