RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.

Build, evaluate and train General Multi-Agent Assistance with ease

A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations. Leveraging the capabilities of large language models (LLMs).

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations. Leveraging the capabilities of large language models (LLMs).

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

The simplest way to serve AI/ML models in production

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

AI equity research agent with resilient workflows, Redis Lua single-flight, pgvector RAG, versioned reports, evidence tracing, and RAG evaluation.

Free AI Desktop Agent for Windows, macOS & Linux - Automate email, calendar, browser, code generation. 13+ AI providers, Ollama, Telegram remote control. No Docker, no terminal. 🦎

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

The open-source Playwright library for AI browser regression testing with intelligent caching, auto-healing, and multi-model verification.

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

An autonomous agent that takes work, does work, gets paid, and gets better at it.

A Framework for Speech, Language, Audio, Music Processing with Large Language Model

The open source post-building layer for agents. Our environment data and evals power agent post-training (RL, SFT) and monitoring.

Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

Hexabot v3 is an automation platform with first-class AI capabilities, combining workflows, actions, and conversational channels in one runtime.

Hexabot v3 is an AI automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

A throughput-oriented high-performance serving framework for LLMs

WHartTest 是一款AI驱动的测试自动化平台，实现从需求到可执行测试用例的自动化生成与管理，帮助测试团队提升效率与覆盖率。 (WHartTest is an AI-driven test automation platform that automates the generation and management of executable test cases from requirements, helping testing teams improve efficiency and coverage.)

The Typescript MCP Framework

Agentic testing for agentic codebases

A highly optimized LLM inference acceleration engine for Llama and its variants.

Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and structured outputs—in just 10 lines of code.

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

A scalable inference server for models optimized with OpenVINO™

Browser automation system that uses AI-driven planning to navigate web pages and perform goals.

The foundation layer for agentic intelligence.

Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.

An open-source computer vision framework to build and deploy apps in minutes

Model Deployment at Scale on Kubernetes 🦄️

MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

A curated collection of awesome AI Agents and LLM Apps built with multiple tech stacks, showcasing real-world implementations using OpenAI, Gemini, local models, and various AI frameworks.

Blades is a Go-based multimodal AI Agent framework.

Framework for enhancing LLMs for RAG tasks using fine-tuning.

End-to-end Generative Optimization for AI Agents

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

Serverless LLM Serving for Everyone.

Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference