Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.

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

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

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

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

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

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

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.

Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs

Fast GPU OCR server. 270 img/s on FUNSD. TensorRT FP16, PP-OCRv5, HTTP + gRPC.

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

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.)

A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem

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

SGLang-Omni empowers high-performance serving for TTS, ASR, speech and omni models.

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

Agentic testing for agentic codebases

The Typescript MCP Framework

“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。

A scalable inference server for models optimized with OpenVINO™

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

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

Mock everything your AI app talks to — LLM APIs, MCP, A2A, vector DBs, search. One package, one port, zero dependencies.

The self-improving Agentic QA harness with Memory. Write tests in natural language.
 Catch regressions before releases ship.

The foundation layer for agentic intelligence.

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

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

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

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

Model Deployment at Scale on Kubernetes 🦄️

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.

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

Blades is a Go-based multimodal AI Agent framework.

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

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

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.

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.

Serverless LLM Serving for Everyone.

A test runner for agentskills.io-style AI agent skills

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

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.

Unified Go interface for Language Model (LLM) providers. Simplifies LLM integration with flexible prompt management and common task functions.

A framework-agnostic, git-native standard for defining AI agents

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2