Havuz

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T

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

Native Linux desktop control for AI agents (MCP, Pi, CLI): semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KDE

面向企业的数字员工构建与运行平台：把专业员工的经验、流程与判断标准，固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache co

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, meter

The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents, AI Models, and MCP Servers. S

Get FAR MORE done with FAR FEWER tokens 🔥

Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.

LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.

Find zero-days while you sleep. DeepZero is an automated vulnerability research framework that parses, decompiles, and analyzes thousands of

Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Fac

Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts

50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infographics, build landing pages,

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

Codex for Android, iOS & Mac. | Aether 扶摇

The open source Unity Dev Agent

MathCode: A Frontier Mathematical Coding Agent

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's patter

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential con

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

CLI, SDK, and IDE plugins for Duel Agents

⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on No

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimiz

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until a

A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path toward

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while

A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

#1 open-source code reviewer on Code-Review-Bench

A minimal modern terminal for AI coding experience — Sidebar workspaces; horizontal / vertical split panes; one-click agent launch; per-agen

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

SDK for Frontier Embedded Agents.

Agent! now supports macOS 14.6 or later, Apple Silicon and Intel, latest release. The Best AI agent for Mac: drives any app via Accessibilit

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

Open-Source Software factory for Open Models

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend

End-to-end AI-powered academic paper writing system — from idea generation and literature search to experiment execution, result backfill, a