Open Source LLM Projects
Discover 273 open source LLM repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. LLM projects here are most often combined with Python, AI Agents and AI. Last updated October 4, 2026.
273 repositories · updated October 4, 2026
learn-claude-code: Learn to Build LLM Agent Harnesses
A hands-on Python tutorial for building the harness around an LLM coding agent, from a basic tool loop to permissions, memory, teams, and workflows. Suited to developers who want to understand agent infrastructure by studying small runnable examples.
page-assist: Use Local AI Models While Browsing
Page Assist is a browser extension that connects a sidebar and chat interface to local AI models. It suits people who want to ask questions about webpages or chat with models through Ollama and compatible endpoints.
rocketnotes: Write and Organize Notes with AI
Rocketnotes is a Markdown notes app that combines hierarchical documents and search with AI features such as document chat, writing completion, and note archiving. Use it as a hosted web or Electron app, or run it locally with Docker.
vllm-cli: Manage and Serve LLMs with vLLM
vllm-cli provides interactive and command-line workflows for configuring and running vLLM model servers. It is aimed at developers and self-hosters who want model discovery, reusable profiles, and server monitoring in one terminal tool.
lagent: Build LLM-Powered Agents in Python
Lagent is a Python framework for composing LLM agents, tools, memory, and multi-agent workflows. It suits developers building tool-using or collaborative agent applications who want synchronous and asynchronous interfaces.
lmql: Program LLMs with Python-Like Constraints
LMQL combines Python-style control flow with language-model queries and constraints on generated text. It suits developers building structured, model-driven workflows who need more control than prompt templates provide.
turboseek: Build an AI Search Engine with Web Sources
TurboSeek is a TypeScript web app that answers questions using web search results and language models. It is suited to developers who want to explore or adapt a Perplexity-style search experience, with external API credentials required to run it.
mcp-server-chart: Generate Charts Through MCP
A TypeScript MCP server that lets AI clients generate AntV visualizations and use them for data analysis. It suits people who want chart generation as an MCP tool, with support for more than 25 chart types and multiple transports.
bolt.diy: Build Full-Stack Apps with Your Choice of LLM
bolt.diy is a browser-based AI coding workspace for creating, editing, and deploying Node.js web applications. It connects to many hosted and local model providers, making it useful when you want control over which LLM powers your development workflow.
agentic_security: Scan LLMs and Agent Workflows for Vulnerabilities
Agentic Security is a Python toolkit for probing LLMs and agent workflows with jailbreaks, fuzzing, and multimodal inputs. It fits developers and security teams who want to run configurable scans against an API and use the results in CI.
Qwen3-Coder: Generate Code and Power Coding Agents
Qwen3-Coder is Qwen’s family of code-focused language models for code generation, repository-scale understanding, and agentic development tasks. It offers open-weight checkpoints in several sizes, with context lengths up to 256K tokens.
AstrBot: Build AI Chatbots for Messaging Platforms
AstrBot is a Python platform for connecting AI models, agents, and plugins to messaging apps through one chatbot framework. It suits individuals and teams building conversational assistants in existing chat workflows, with a WebUI and deployment options including Docker.