LLM & Inference

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

Create, Evaluate, and Connect AI Skills

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit!

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

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

LLMs as Copilots for Theorem Proving in Lean

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军

Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

The official implementation of Self-Play Fine-Tuning (SPIN)

Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow.

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

Official Inference Code of EAGLE-4

EvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ EvoOntology插件为Claude Code/Codex 建立&进化本体层

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

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

从 NLP 到 LLM 的算法全栈教程，在线阅读地址：https://datawhalechina.github.io/base-llm/

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on grandet.ai.

100+ LLM interview questions with answers.

Implementing LLM architectures from scratch in PyTorch

把英文论文读成舒服的中文：本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.

An AI second brain that maintains itself. Full guide, starter vault, agent skills and scripts for a self-organizing knowledge base in Claude Code and Obsidian.

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

[TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

🌟 A curated collection of free, high quality AI tools 🤖, APIs 🔗, datasets 📊, and learning resources 📚 covering machine learning 🧠, deep learning 🧩, generative AI 🎨, NLP 💬, and data science 📈. Designed to help developers 👩‍💻, researchers 🔬, and creators ✨ explore and build with AI faster ⚡.

“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。

麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。

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!

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

A throughput-oriented high-performance serving framework for LLMs

AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration.

AI 跨境电商运营智能体工具箱 · 把运营 SOP 拆成 7 个可复用的 AI Agent 工作流，含 Prompt、模板与真实案例

List of awesome hosting sorted by minimal plan price

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)