Awesome Opensource Ai

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Ecommerce Search and Discovery - marqo.ai

AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.

Agenta is a workspace where you and your team build agents and automations.

Align Anything: Training All-modality Model with Feedback

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Reliable Multi-Agent Orchestration Framework

A light-weight, flexible, and expressive statistical data testing library

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

A nearly-live implementation of OpenAI's Whisper.

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

AdalFlow: The library to build & auto-optimize LLM applications.

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

A system for agentic LLM-powered data processing and ETL

OpenAgents - AI Agent Networks for Open Collaboration

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Generative models for conditional audio generation

Framework for evaluating and improving agents

Open-source security automation platform for teams and AI agents

Open-source multimodal retrieval engine (Morphik Core). By Morphik — AI back office for skilled nursing & senior living (morphik.ai).

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.

Evaluation and Tracking for LLM Experiments and AI Agents

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

II-Agent: a new open-source framework to build and deploy intelligent agents

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

The Security Toolkit for LLM Interactions

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

An Open Standard for lineage metadata collection

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Inspect: A framework for large language model evaluations

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Fully open data curation for reasoning models

An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Manages Unified Access to Generative AI Services built on Envoy Gateway

Scalable toolkit for efficient model reinforcement

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models