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
phoenix: Observe and Evaluate AI Applications
Arize Phoenix is a self-hosted platform for tracing, evaluating, and troubleshooting LLM applications. It helps AI engineers inspect runtime behavior and test changes to prompts, models, and retrieval.
observers: Track and Store AI API Interactions
Observers wraps generative AI clients to capture interactions and sync them to storage backends. It suits Python teams that need lightweight observability across supported LLM providers, with storage options ranging from DuckDB to OpenTelemetry-compatible services.
freellmapi: Route LLM Requests Through One API
FreeLLMAPI is a self-hosted TypeScript router that combines free LLM provider accounts and custom OpenAI-compatible endpoints behind one API. It selects models, tracks quotas, and retries across providers, mainly for personal experimentation and development.
guardrails: Validate LLM Inputs and Outputs
Guardrails is a Python framework for checking LLM inputs and outputs against configurable validators and for generating structured data. It suits teams building AI applications that need validation and error handling around model responses.
hiring-agent: Score Resumes with AI and GitHub Signals
Hiring Agent turns PDF resumes into structured profiles, enriches them with GitHub data, and scores them against configurable role rubrics. It is for teams exploring explainable resume prioritization, with human review remaining essential.
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.
odysseus: Run a Self-Hosted AI Workspace
Odysseus brings AI chat, agents, research, documents, email, notes, and calendar tools into a self-hosted workspace. It suits people who want one place to work with local or API-connected models and control their own deployment.
headroom: Compress Context for AI Agents
Headroom compresses tool outputs, logs, files, and retrieval context before they reach an LLM, helping reduce token use while retaining important details. It offers local library, proxy, and MCP integrations for agent workflows.
voicebox: Create and Use AI Voices Locally
Voicebox is a desktop voice studio for local speech generation, voice cloning, dictation, and agent audio. It suits creators and developers who want voice tools and integrations on their own machine, with hardware and platform capabilities varying by setup.
easy-whisper-ui: Transcribe Audio and Video Locally
EasyWhisperUI is a desktop app for transcribing audio and video locally with whisper.cpp. It offers batch and live transcription, subtitle and text exports, and GPU acceleration where supported, without requiring command-line use.
PixelRAG: Search Documents by Their Visual Content
PixelRAG indexes screenshots of web pages and documents for visual retrieval, preserving charts, tables, and layout that text extraction can lose. It offers a Python pipeline, command-line renderer, and hosted search API.
open-pencil: Edit and Automate Design Files
OpenPencil is an AI-assisted design editor for opening and editing .fig and .pen files. It combines a visual canvas with CLI, MCP, and scripting tools for design workflows, plus real-time collaboration and a headless Vue SDK.