A skill that guides an agent to restore local patches and feature toggles disabled after a Codex Desktop upgrade on Windows (computer use, plugins, jailbreaks, forced Chinese localization for Codex, fast mode, remote phone control, vanishing sessions, etc.), with support for auto-updating to the latest skill version.
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
The open-source Playwright library for AI browser regression testing with intelligent caching, auto-healing, and multi-model verification.
HiMarket is an enterprise-level "AI Capability Marketplace and Developer Ecosystem Hub." It is not merely a simple aggregation of traditional APIs, but rather a comprehensive platform that packages, publishes, manages, and operates core AI assets such as enterprise Model APIs, MCP Servers, Agent APIs, etc., through standardized product formats.
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)
Evaluate and improve models and agents using environments
An AI knowledge base/agent built with .Net 9, AntBlazor, Semantic Kernel, and Kernel Memory, supporting local offline AI large models. It can run offline without an internet connection. Supports Aspire for monitoring application data.
Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB
Your Software Factory - build faster and better with multi node agents that work 24/7.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
OpenCode plugin that uses your existing Claude Code credentials — no separate login needed.
Find and build open-source alternatives
AWS-native chatbot using Bedrock
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.
13 AI Skills that ingest Chinese multi-platform content (Douyin, Bilibili, Xiaohongshu, WeChat official accounts, X, podcasts) into your personal knowledge base: image/video routing and subtitle-first transcription with no GPU needed, plus a knowledge-base MCP server.
An elegent pytorch implement of transformers
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token and context wastage.
Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.
local-first semantic code search engine
Turn your local files into a Wiki for your agents. Open-source and local-first.