Awesome Opensource Ai

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Streamlit — A faster way to build and share data apps.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Build resilient agents.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Self-hosted AI coding assistant

Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents

Label Studio is a multi-type data labeling and annotation tool with standardized output format

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

A high-performance observability data pipeline.

A guidance language for controlling large language models.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

open-source agentic AI data assistant for the next generation of AI + Data products.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The LLM Evaluation Framework

Workflow Engine for Kubernetes

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

An orchestration platform for the development, production, and observation of data assets.

The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.

The developer platform for on-demand cloud development environments to create software faster and more securely.

LangGPT: Empowering everyone to become a prompt expert! 🚀 📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者 📌 最流行的提示词落地范式 | Language of GPT The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide Created by 云中江树

The Context Platform for your Data and AI Stack

OpenRefine is a free, open source power tool for working with messy data and improving it

Always know what to expect from your data.

Cloud-native OSS search engine for observability

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Open source annotation tool for machine learning practitioners.

the LLM vulnerability scanner

🧙 Build, run, and manage data pipelines for integrating and transforming data.

Apache Beam is a unified programming model for Batch and Streaming data processing.

Build effective agents using Model Context Protocol and simple workflow patterns

An app that brings language models directly to your phone.

The Open Source Feature Store for AI/ML

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Model interpretability and understanding for PyTorch

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

Simple and Distributed Machine Learning

Visualizer for pandas data structures

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

Set of tools to assess and improve LLM security.

OpenAgents - AI Agent Networks for Open Collaboration

Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).

Build production-ready AI agents in both Python and Typescript.

Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.

DeepTeam is a framework to red team LLMs and AI agents.