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
deepagents: Build Agents with Planning and Tooling Built In
Deep Agents is a Python agent harness for building LLM agents with planning, delegation, file access, and context management built in. It suits developers who need a more capable starting point than a minimal agent loop, while retaining control over models and tools.
mcp-ui: Build Interactive Interfaces for MCP Tools
mcp-ui provides SDKs for attaching web interfaces to Model Context Protocol tools and rendering them in compatible hosts. Use it when an MCP server needs interactive, sandboxed UI alongside tool results.
langcorn: Serve LangChain Apps as FastAPI APIs
LangCorn turns LangChain chains, agents, and custom run functions into FastAPI endpoints. It suits developers who want to expose existing language-model workflows through a documented REST API with optional token authentication.
helicone: Monitor and Route LLM Requests
Helicone is an LLM observability platform and AI gateway for teams building AI applications. It helps developers inspect requests, track costs and latency, evaluate outputs, and route traffic across model providers.
KBLaM: Add Knowledge Bases to Language Models
KBLaM is a research implementation for giving transformer language models access to external knowledge through learned adapters and special knowledge tokens. It is aimed at researchers testing knowledge-grounded answers without a separate retrieval module.
vanna: Turn Natural-Language Questions into SQL Insights
Vanna helps teams build chat interfaces that translate natural-language questions into SQL and return streamed tables, charts, and summaries. It is aimed at applications that need database-backed answers with user-aware permissions and an embedded web UI.
LLocalSearch: Search the Web with Local LLM Agents
LLocalSearch is a self-hosted search app that uses locally running language models and tools to research questions on the web. It suits people who want current answers with visible agent activity and without OpenAI or Google API keys.
chat-ui: Build a Web Interface for OpenAI-Compatible LLMs
Chat UI is a SvelteKit application for chatting with models through OpenAI-compatible APIs. It powers HuggingChat and can be self-hosted with a compatible model service, optional MongoDB, and configurable tools.
Awesome-AI-Agents: Explore LLM Agent Projects and Tools
A curated, searchable directory of autonomous and multi-agent projects, frameworks, benchmarks, platforms, and supporting tools powered by LLMs. Use it to survey the ecosystem and find projects relevant to a particular agent-building need.
ai-baby-monitor: Local AI Video Monitoring for Baby Safety
A self-hosted baby-monitoring tool that checks webcam or RTSP video against natural-language safety rules using a local video LLM. It sends a quiet beep when a rule appears to be broken, with a dashboard for viewing the stream and model logs.
HiveChat: Team AI Chat with Multiple Model Providers
HiveChat is a deployable AI chat app for small and medium-sized teams. Administrators configure model providers, access methods, user groups, and monthly token limits, while team members use a shared chat interface.
verifiers: Build Environments for LLM Training and Evaluation
verifiers is a Python library for building environments to train and evaluate large language models. It fits teams developing LLM reinforcement-learning workflows or reusable evaluations, especially those using Prime Intellect's training tools.