LLM & Inference

🧱 Experimental library for building inference engines

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Open-source local AI workspace — advancing on-device inference.

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.

和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）

活字通用大模型

BentoDiffusion: A collection of diffusion models served with BentoML

A 2007 Nokia can't search Google anymore, so I gave it Claude, ChatGPT, Gemini and Grok. J2ME app for Nokia S40/S60 + tiny Go server.

Build a ChatGPT like LLM from scratch in PyTorch, explained step by step.

🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.

🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill splitting.

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

Open-source Autonomous 3D Characters on the Web

The open-source Devin alternative. Run Claude Code, Codex or OpenCode in isolated cloud workspaces you can self-host.

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

AI coding agent that makes a small model beat a frontier one

让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token

零基础入门 AI Agent 的基础教程。不只是教程，也是一个能在本地跑起来的 Agent：读写文件、执行命令、MCP、长期记忆，自带网页端看清每一步。从 100 行最小循环开始，一课加一个能力，最后拆解 Claude Code、Codex 等主流 Agent

An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Walk through a diff the way a senior engineer reads it. A read-only TUI that turns a git change into a guided tour.

Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.

Production-ready data processing made easy and shareable

1894 live x.ai/bot shares for Grok Bot — every link status-checked, every row attributed. Bilingual EN/中文 catalog with a JSON schema, CI, and a searchable site.

🚀🚀🚀 [ICML 2026] Official Implementation of Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.

Replay your coding agent sessions as a map and a timeline

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

100% free, open-source personal agents for your messaging apps, tools, and services

Qwen3 Fine-tuning: Medical R1 Style Chat

Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big dump in the Image Bank), curate, caption, clean watermarks, then train LoRAs on five model families or a full Krea 2 model on a rented GPU, and rank checkpoints in a Test Studio. Free & local.

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

在 Android 手机上本地部署和管理 AstrBot 与 NapCat，内置 PRoot Ubuntu 运行环境，支持原生管理界面、WebUI、日志、备份恢复和独立更新，无需 Root。

A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.

Lossless AI compression: 33% less GPU memory, bit for bit.

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

Local inference for diffusion language models (LLaDA, Dream), written in Mojo

The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.

A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous case study. MIT licensed, no signup. By Zorost Intelligence AI Lab.

数据面具 Data Maskit — 专为大模型打造的本地隐私脱敏网关（请求自动打码，回复流式还原；支持 Cursor / Claude Code / Codex / Pi 等任意可配 Base URL 工具）

OSS trading workspace with your favorite agents