Open Source AI & Machine Learning Projects

Private, in-browser AI summarizer for articles, videos, and PDFs that runs entirely on-device via WebGPU, WebAssembly, or a local Ollama instance.

Self-hosted service that turns saved articles and documents into a private podcast feed with cloned-voice narration.

Open LLM app platform with visual workflows, RAG pipeline, agents and model management. Deploy self-hosted, in your VPC, or on Dify Cloud.

Open source AI gateway and router that exposes hosted, BYOK, local, and custom models through one OpenAI-compatible API.

Private, self-hosted search engine that indexes the pages you visit and the files you keep for full-text and semantic search.

Free, MIT-licensed desktop AI assistant that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows, and Linux.

Visually build and deploy AI agents and workflows in Python, with built-in API and MCP servers. MIT-licensed and backed by DataStax.

Open-source AI chat and agent platform with multi-provider support, RAG, plugins, and an agent marketplace — self-hostable ChatGPT alternative.

Open platform for governing execution authority at decision surfaces across agents, AI systems, and enterprise workflows.

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

Open-source managed agent platform for running AI agents on any model and any machine, self-hostable via Docker.

Onyx is an open-source AI chat and enterprise search platform with RAG that works with every LLM. Bring your own model, connect your tools, and unify all your team's knowledge.

Open-source, privacy-first alternative to Google NotebookLM with multi-model AI support, podcast generation, and self-hosting.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Sim is an open-source workspace to build, deploy, and orchestrate AI agents and agentic workflows. Visually connect LLMs, tools, and data sources without giving up control.

Self-hosted AI transcription and intelligent note-taking platform that turns audio recordings into organized, searchable notes with speaker identification.

Open-source workspace where teams and AI agents plan tasks, run them in sandboxes, and review results together.

Open-source platform for fine-tuning and running LLMs locally — 2x faster training with 70% less VRAM. Supports LoRA, QLoRA, DPO, GRPO.

Fully local voice cloning, dubbing, dictation, and transcription in one desktop app - an open-source ElevenLabs replacement.

AI-native design editor with real-time collaboration, component system, and Figma-compatible file format.