Open Source AI Projects
Discover 275 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.
275 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.
n8n: Build Visual Workflows and AI Agents
n8n connects apps and services in visual workflows, with custom code available for more complex automation. It suits teams that want to build AI-enabled processes and choose between self-hosting and cloud deployment.
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.
vscode-copilot-chat: AI Coding Assistance in VS Code
An archived Microsoft repository for GitHub Copilot Chat in Visual Studio Code, offering agent-based task execution, inline suggestions, and focused editing. Active development has moved to the main VS Code repository.
vggt: Reconstruct 3D Scenes from Images
VGGT is a feed-forward vision model that estimates cameras, depth, point maps, and point tracks from one or more images. It suits researchers and developers who need fast 3D scene reconstruction without a traditional multi-stage pipeline.
ClickUi: A Desktop Assistant for Chatting with AI Models
ClickUi is a Python desktop assistant that opens with a hotkey and supports text and voice conversations with local or API-based AI models. It suits people who want AI tools available alongside their everyday computer work.
typescript-sdk: Build Model Context Protocol Clients and Servers
The official TypeScript SDK for building Model Context Protocol clients and servers. It provides transports, server and client libraries, and optional framework adapters for applications that exchange context with LLMs through MCP.
MuseTalk: Generate Audio-Synced Talking-Head Videos
MuseTalk creates lip-synced video from a source video or image and an audio clip using latent-space inpainting. It supports training and inference workflows, with real-time performance reported on a Tesla V100.
cursor-memory-bank: Structure AI-Assisted Development Workflows
cursor-memory-bank adds a persistent task memory and phased workflow to Cursor, guiding projects from initialization and planning through implementation and review. It suits developers who want repeatable processes and durable context for AI-assisted coding.
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.
x: Build AI Interfaces with React Components
Ant Design X is a TypeScript component and tooling suite for building AI-powered interfaces with React. It provides conversation UI, streaming data utilities, Markdown rendering, and dynamic cards, so teams can focus on integrating their AI experiences rather than assembling these pieces from scratch.
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.