Open Source Generative AI Projects
Discover 68 open source Generative AI repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Generative AI projects here are most often combined with Python, Machine Learning and AI. Last updated October 3, 2026.
68 repositories · updated October 3, 2026
EasyInstruct: Generate, Select, and Prompt LLM Instructions
EasyInstruct is a Python framework for preparing instruction data and prompts for large language model research. It combines instruction generation and dataset selection tools with prompt and local-model execution modules.
OpenMontage: Produce Videos with AI Coding Assistants
OpenMontage gives AI coding assistants structured pipelines for researching, scripting, generating assets, editing, and rendering videos. It suits creators and developers who want to automate production while retaining control over choices and approvals.
frontend-slides: Create HTML Presentations with a Coding Agent
Frontend Slides is an agent skill for building styled web presentations from a brief or an existing PowerPoint. It suits people who want to choose a visual direction without writing CSS, then customize or share the resulting HTML deck.
xgrammar: Constrain Language Model Output to Structured Formats
XGrammar is a library for constrained decoding that helps language models produce outputs matching JSON, regular expressions, or context-free grammars. It suits teams integrating structured output into LLM inference and applications that need reliable machine-readable responses.
jsonformer: Generate Schema-Conforming JSON with Language Models
Jsonformer guides Hugging Face language models to produce JSON that matches a supplied schema by generating variable content while inserting predictable structure itself. It suits developers who need structured model output and can work within its supported JSON Schema subset.
AuditNLG: Check and Improve Trust in Generated Text
AuditNLG is a Python library for evaluating generated text for factualness, safety, and instruction compliance. It combines model- and API-based checks with explanations and rewrite suggestions for research and language-model application teams.
palmier-pro: Edit Video with AI on macOS
Palmier Pro is a Swift-native macOS video editor that combines timeline editing with generative AI and MCP access for AI agents. It suits creators who want to generate or edit media alongside agent-assisted workflows on Apple Silicon.
Qwen3-VL: Understand Images, Video, and Text with Multimodal Models
Qwen3-VL is a family of multimodal language models for interpreting images, video, and text. The repository provides inference examples, deployment guidance, and cookbooks for tasks such as OCR, spatial reasoning, and visual agents.
Open-Higgsfield-AI: Review and Run an AI Image Studio
A JavaScript-based AI image studio presented as a self-hosted alternative to Higgsfield AI. The repository currently describes the app as an internal review tool, with image generation paused until provider credits are available.
VoxCPM: Generate and Clone Multilingual Speech
VoxCPM is a tokenizer-free text-to-speech system for multilingual speech generation, voice design, and voice cloning. Its VoxCPM2 release targets teams and developers who need expressive speech synthesis and can support a 2B-parameter model.
MOSS-TTS: Generate Speech, Dialogue, and Sound with AI
MOSS-TTS is a family of speech and sound generation models for long-form narration, voice cloning, dialogue, voice design, sound effects, and streaming TTS. It offers multiple model architectures and deployment paths for research, production, and local inference.
open-carrusel: Design Instagram Carousels with Claude
Open Carrusel is a local-first web app for creating Instagram carousel slides through conversations with Claude Code. Preview, reorder, and export slides as PNGs sized for Instagram.