| HKUDS/nanobot | 49,041 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps |
|---|
| mozilla-ai/llamafile | 26,249 | Distribute and run LLMs with a single file. |
|---|
| LearningCircuit/local-deep-research | 9,192 | ~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. |
|---|
| MakazhanAlpamys/Soup | 9,048 | Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
|---|
| open-multi-agent/open-multi-agent | 7,001 | Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. |
|---|
| dograh-hq/dograh | 5,873 | 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. |
|---|
| maziyarpanahi/openmed | 5,687 | Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK. |
|---|
| vinta/pangu.js | 4,851 | Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment |
|---|
| langroid/langroid | 4,113 | Harness LLMs with Multi-Agent Programming |
|---|
| raullenchai/Rapid-MLX | 3,981 | Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights. |
|---|