#llm

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

🙌 OpenHands: AI-Driven Development

🚀 The fast, Pythonic way to build MCP servers and clients.

A React Rich Text Editor that's block-based (Notion style) and extensible. Built on top of Prosemirror and Tiptap.

Python SDK for ACP clients and agents.

Build and run agents you can see, understand and trust.

Go ahead and axolotl questions

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Accessible large language models via k-bit quantization for PyTorch.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Dynamiq is an orchestration framework for agentic AI and LLM applications

Open-source, secure environment with real-world tools for enterprise-grade agents.

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Pretrained model hub for Keras 3.

Low-code framework for building custom LLMs, neural networks, and other AI models

A modular graph-based Retrieval-Augmented Generation (RAG) system

Communicate with an LLM provider using a single interface

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

A set of tools that gives agents powerful capabilities.

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

runs anywhere. uses anything

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

The agent that grows with you

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.