Open Source AI Projects
Discover 281 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.
281 repositories · updated October 4, 2026
awesome-ai: Browse a Curated Directory of AI Tools
A categorized directory of AI APIs, tools, frameworks, platforms, and learning resources. Use it to explore options across AI development, deployment, evaluation, and education, then verify each tool’s current status before adoption.
ext-apps: Add Interactive UIs to MCP Tools
MCP Apps is a specification and TypeScript SDK for serving interactive interfaces from MCP servers inside compatible AI chat clients. It helps server and client developers connect tool results to sandboxed, bidirectional UI experiences.
AsterMind-ELM: Build Lightweight JavaScript ELM Models
AsterMind-ELM is a TypeScript library for training and using Extreme Learning Machines in browser and Node.js applications. It supports kernel, online, and stacked ELMs for compact, on-device classification, regression, and embedding workflows.
copilot.vim: Get AI Code Suggestions in Vim and Neovim
copilot.vim integrates GitHub Copilot into Vim and Neovim, showing coding suggestions inline as you work. It suits developers who want Copilot in their editor and have an active Copilot subscription.
Speech: Build and Deploy Speech AI Models
NVIDIA NeMo Speech is a Python framework for researchers and developers building speech recognition, text-to-speech, and speech language models. Use it to train, customize, and run speech models with PyTorch and pretrained checkpoints.
colibri: Run Large MoE Models on Local Hardware
colibri is a C inference engine that streams Mixture-of-Experts model weights from disk, so large models can run without fitting entirely in RAM or VRAM. It supports CPU-only use and optional GPU backends, with speed depending on hardware and storage.
axolotl: Fine-Tune Large Language Models
Axolotl is a Python framework for fine-tuning and post-training language models through configurable workflows. It supports methods from LoRA and QLoRA to preference tuning and reinforcement learning, with options for multimodal and distributed training.
app.yumcut.com: Generate Short Videos from Prompts
YumCut turns a prompt into a vertical short video with generated scripts, voice, visuals, and captions. It is aimed at creators and teams who want to automate short-form production and control their deployment and provider choices.
lamini: Access the Lamini API from Python
Lamini is a Python client and SDK for working with Lamini's generative AI API. It suits developers who want to connect Python applications to Lamini without building API requests from scratch.
zero: Run a Local Terminal Coding Agent
Zero is a Go-based terminal coding agent that can inspect and edit repositories, run commands, and work with many hosted or local models. It suits developers who want scriptable coding assistance with local sessions and explicit controls over side effects.
griptape: Build AI Agents and Workflows in Python
Griptape is a modular Python framework for building generative AI applications with tasks, agents, pipelines, and workflows. It suits developers who want to combine language models with tools, memory, and retrieval components through swappable integrations.
memoripy: Build Evidence-Based Memory for AI Agents
Memoripy is a local memory runtime for AI agents that keeps versioned, sourced records and explains why they appear in recall. It suits developers who need scoped, auditable memory rather than an opaque store of accumulated text.