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
asta-paper-finder: Find Papers from Natural-Language Queries
PaperFinder is a single-query research agent that finds papers using content and metadata criteria, then judges and ranks results. This frozen evaluation release is suited to reproducing results or running the core workflow locally, rather than replacing the live service.
harness-sdk: Build and Run AI Agents in Python and TypeScript
Strands Agents provides Python and TypeScript tools for building AI agents, from a ready-made harness to a customizable agent SDK. It suits teams that want model flexibility and control over agent execution without a hosted control plane.
Kimi-k1.5: Train Multimodal LLMs with Reinforcement Learning
Kimi k1.5 is a research project describing reinforcement learning methods for training long-context, multimodal language models. It is aimed at researchers studying LLM reasoning and training, rather than users looking for a ready-to-install model.
otto: Add LLM-Powered Automation to Frappe Apps
Otto is an experimental Frappe app and Python library for connecting language models to Frappe workflows. It supports task automation, custom assistants, tool use, and resumable LLM sessions.
pocketpal-ai: Run Language Models on Your Phone
PocketPal AI is a mobile assistant that runs language models and text-to-speech on-device, so chats can stay private and work offline. It suits people who want local AI on iOS or Android without relying on a cloud service.
judges: Evaluate LLM Outputs with Reusable AI Judges
Databricks judges is a Python library for evaluating language model outputs with reusable LLM-based classifiers and graders. Use its research-backed judges, combine evaluations with a jury, or build a custom judge for your task.
Open-Interface: Control Your Computer with LLMs
Open-Interface turns natural-language requests into simulated mouse and keyboard actions, using screenshots and an LLM to guide and correct its work. It suits people who want to automate desktop tasks and are comfortable granting screen and input permissions.
Qwen-Agent: Build Tool-Using LLM Applications
Qwen-Agent is a Python framework for building Qwen-based assistants that can call tools, plan tasks, and work with documents. Use it to prototype or deploy agent applications when you need integrations such as MCP, code execution, or retrieval-augmented generation.
byterover-cli: Give Coding Agents Persistent Project Memory
ByteRover CLI helps AI coding agents retain structured project knowledge across sessions. Developers can curate, query, and version context locally, with optional cloud sync and integrations for coding tools.
OxyGent: Build Modular Multi-Agent AI Systems
OxyGent is a Python framework for assembling tools, language models, and agents into modular multi-agent systems. It suits developers who need reusable components, configurable agent collaboration, and observable execution paths.
opik-mcp: Connect AI Assistants to Opik
opik-mcp is a Python MCP server that lets AI coding assistants work with an Opik workspace. Use it to inspect traces, record scores, manage prompts, and explore evaluation data through natural-language workflows.
ch.at: Chat with Language Models over Web, SSH, and DNS
ch.at is a lightweight Go chat service that exposes language-model conversations through a web page, HTTP API, SSH, and DNS. It also offers a public, in-memory board for posts and feeds, making it suited to simple, low-dependency deployments and experimental access methods.