Open Source AI Projects
Discover 276 open source AI repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI projects here are most often combined with LLM, Python and TypeScript. Last updated October 4, 2026.
276 repositories · updated October 4, 2026
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.
LAM: Create Animatable 3D Gaussian Avatars from One Image
LAM reconstructs a 3D Gaussian head avatar from a single image and supports animation and rendering across devices. It is aimed at developers building digital humans, especially interactive avatars, and requires model assets and a compatible compute environment for local use.
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.
laravel-claude-code-setup: Configure Claude Code for Laravel
A Shell installer that configures Claude Code and MCP servers for Laravel projects, including database, repository, and Figma integrations. Useful for Laravel developers who want a repeatable AI-assisted development setup.
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.
kilocode: Use AI Coding Agents Across IDEs and CLI
Kilo Code is an AI coding agent for VS Code, JetBrains IDEs, and the command line. It helps developers generate and review code, run tools, and choose among many AI models, with modes for planning, debugging, and codebase questions.
streamdown: Render Markdown During AI Streaming
Streamdown is a React Markdown renderer built for text arriving incrementally from AI models. It handles incomplete Markdown while supporting common formats such as tables, math, diagrams, and highlighted code.
logocreator: Generate Logos and Brand Kits with AI
LogoCreator is a web app for generating and editing logos with AI, then exporting assets for a brand kit. It suits people who need a quick starting point for a new brand and want to run the app themselves with a Together AI API key.
py-priompt: Build Token-Budgeted Prompts in Python
PyPriompt is a Python library for composing LLM prompts from reusable components and selecting content by priority to fit a token limit. It suits developers who need fine-grained control over prompt contents, such as preserving recent conversation history while trimming older context.
subwiz: Discover Subdomains with a Lightweight GPT Model
subwiz uses a small transformer model to predict candidate subdomains from known subdomains, then can check whether predictions resolve. It is aimed at security teams and researchers who want an additional discovery step after passive enumeration.
GPT-SoVITS: Clone Voices and Generate Speech from Text
GPT-SoVITS is a Python toolkit for voice cloning, speech conversion, and text-to-speech. It supports zero-shot synthesis from a short reference clip and fine-tuning with about one minute of voice data, with a WebUI for preparing data and training models.