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
APIPark: Manage AI Models and APIs Through One Gateway
APIPark is an open-source AI gateway and API developer portal for standardizing access to AI models and REST APIs. It helps teams manage API publishing, subscriptions, keys, usage monitoring, and model integrations in one place.
opik: Trace, Evaluate, and Monitor LLM Applications
Opik is a platform for tracing and evaluating LLM applications, RAG systems, and AI agents. Teams can use it to inspect workflows, run evaluations, and monitor deployments, either self-hosted or through Comet Cloud.
Toolkit-for-Prompt-Compression: Evaluate and Apply Prompt Compression
PCToolkit is a Python toolkit for applying and evaluating prompt-compression methods for large language models. It brings five compressors, datasets, and evaluation metrics behind modular interfaces, making it useful for comparing methods across language tasks.
aider: Pair Program with AI in Your Terminal
Aider is a terminal-based AI coding assistant that works with existing repositories or new projects. It helps developers make code changes with cloud or local language models while keeping edits and version control in their workflow.
judgy: Estimate LLM Judge Success Rates with Bias Correction
judgy estimates a system’s true pass rate from human-labeled calibration data and LLM judge predictions. It corrects for judge errors and uses bootstrap resampling to produce a confidence interval, making it useful when evaluating larger unlabeled datasets.
mcp-agent: Build Agents with Model Context Protocol
A Python framework for building LLM agents around Model Context Protocol servers and composable workflow patterns. It suits developers who need MCP integrations, multi-agent workflows, or durable execution with Temporal.
GenerativeAICourse: Learn Generative AI Through Notebook Labs
A notebook-based course introducing generative AI and practical AI engineering, from LLM fundamentals to chatbots, RAG, agents, and MCP. It is aimed at learners who want guided explanations and hands-on Python exercises.
AingDesk: Use AI Models, Knowledge Bases, and Agents
AingDesk is a desktop and server-deployable AI assistant for using model APIs or local models alongside knowledge bases, web search, and agents. It suits people who want these capabilities in one interface, with options to share assistants online.
llm-consortium: Coordinate Multiple LLMs to Refine Answers
llm-consortium is a Python plugin for the llm package that runs multiple language models in parallel, then uses an arbiter to evaluate and synthesize their responses. It suits users who want collaborative model reasoning and configurable consensus workflows.
trae-agent: Delegate Software Engineering Tasks to an AI Agent
Trae Agent is a configurable Python CLI that uses language models and tools to carry out software engineering tasks. It suits developers and researchers who want an extensible agent they can run against a project, inspect through recorded trajectories, and adapt for experiments.
open-notebooklm: Turn PDFs Into Podcast Audio
Open NotebookLM turns a PDF into an AI-generated podcast dialogue and MP3. It suits readers who want an audio-style overview of a document, and requires a Fireworks API key to run.
KAG: Build Knowledge-Grounded Reasoning and Q&A Systems
KAG is a Python framework for building domain-specific question-answering systems that combine knowledge graphs, source text, and LLMs. It targets factual and multi-hop reasoning where vector similarity alone may be insufficient.