Data / Repositories / Local LLM
Local LLM repositories on GitHub: 13 ranked by stars
13 public repositories tagged Local LLM are on GitHub, with 67,023 stars between them; 12 had a push in the last 30 days. Most are written in Python (8), TypeScript (2), C (1). The most starred: HKUDS/nanobot (49,026), LearningCircuit/local-deep-research (9,190), dograh-hq/dograh (5,868).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| HKUDS/nanobot | 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 | 49,026 | 8,629 | MIT | Oct 14 | Oct 14 |
| LearningCircuit/local-deep-research | ~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.… | Python | 9,190 | 845 | MIT | Oct 14 | Oct 14 |
| dograh-hq/dograh | 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… | Python | 5,868 | 1,493 | BSD-2-Clause | Oct 14 | Oct 14 |
| mrkrsl/web-search-mcp | A simple, locally hosted Web Search MCP server for use with Local LLMs | TypeScript | 1,180 | 161 | MIT | Aug 8, 2025 | Oct 14 |
| jonigl/mcp-client-for-ollama | Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching… | Python | 830 | 126 | MIT | Oct 13 | Oct 14 |
| prabanta-dev/janas | 37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M.… | C | 410 | 29 | GPL-3.0 | Oct 14 | Oct 15 |
| ANDRETRIPOL/OpenGhost | Open desktop AI agent for Windows, macOS and Linux, written from scratch: its own agent engine, its own browser tooling and its own drawing engine that shows what it explains. | JavaScript | 267 | 21 | MIT | Oct 15 | Oct 15 |
| VecSzn/PolyStrata | Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost… | C++ | 125 | 25 | MIT | Oct 15 | Oct 15 |
| jonigl/ollama-mcp-bridge | Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for… | Python | 104 | 39 | MIT | Sep 25 | Oct 14 |
| bloom500/cinderpaw | A desktop AI agent that lives on your computer. It works with your files and apps, browses the web where you can watch, remembers what matters to you, and tests ways to get… | TypeScript | 10 | 2 | Apache-2.0 | Oct 12 | Oct 14 |
| shimo4228/contemplative-agent | A long-running experiment: an AI agent posts on its own with a local LLM (Ollama, one 16 GB Mac) and proposes changes to its harness (the constitution, identity and skills in its… | Python | 7 | 2 | MIT | Oct 14 | Oct 14 |
| nicotem/exegete | Exegete: full feature, qualitative data analysis through a conversation with your AI assistant, compatible with QualCoder projects. Runs on your computer as an MCP server… | Python | 6 | 0 | LGPL-3.0 | Oct 14 | Oct 14 |
| munimtechnologies/self-hosted-ai-security-checklist | Safe defaults and one-line tests for self-hosted AI: Ollama, Open WebUI, vLLM, LiteLLM, ComfyUI, n8n, Dify, Langflow, Flowise, RAGFlow, AnythingLLM. By MV2 of Munim, Inc., with AI… | Python | 0 | 0 | Oct 14 | Oct 14 |
By language
- Python 8
Related topics
- LLM 6
- MCP 6
- AI agents 5
- Self hosted 5
- Ollama 5
- Model Context Protocol 4
- Python 4
- AI 3
- Linux 3
- Agent framework 2
- LLM agents 2
- Anthropic 2
Read from GitHub by SpecStream between October 14, 2026 and October 15, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.