Awesome Opensource Ai

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

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

Bonsai Demo

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

A framework for prompt tuning using Intent-based Prompt Calibration

Inspect: A framework for large language model evaluations

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

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

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.

Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Community maintained hardware plugin for vLLM on Ascend

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.

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.

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Data Contracts engine for the modern data stack. https://www.soda.io

Self-learning agent browser

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

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

An implementation of chunked, compressed, N-dimensional arrays for Python.

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

Agentic RL Training at Scale

Scalable toolkit for efficient model reinforcement

ContextGem: Effortless LLM extraction from documents

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Large-scale LLM inference engine

Lightweight and extensible compatibility layer between dataframe libraries!

MLRun is an open source MLOps platform for quickly building and managing continuous ML applications across their lifecycle. MLRun integrates into your development and CI/CD environment and automates the delivery of production data, ML pipelines, and online applications.

A fast and lightweight framework for creating decentralized agents with ease.

The LLM Anti-Framework

bloom - evaluate any behavior immediately  🌸🌱

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

Scalable machine 🤖 learning for time series forecasting.

XAI - An eXplainability toolbox for machine learning

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Readymade evaluators for your LLM apps

Lightning fast data version control system for large repositories of data. Feels like git, pushes and pulls like oxen.

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

Hierarchical agent loops with recursive self-organization.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

Self-Programming AI Agent Framework. Agents create and refine their own workflows.