LiveBench
LiveBench: A Challenging, Contamination-Free LLM Benchmark
LiveBench: A Challenging, Contamination-Free LLM Benchmark
AI-ready reference architecture for Angular / ASP.NET Core projects. A hardened foundation with secure authentication, authorization, role and user management, and consistent patterns designed to be safely extended by AI tools. Stop letting AI hallucinate your auth and DB logic - give it a production-grade foundation to build on.
extract all your personal data history from cursor, codex, claude-code, windsurf, and trae
A starter kit for building ai agents on Cloudflare
A collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric
OpenClaw alternative in your pocket
Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.
Tutorial for Poe server bots
An expression-training system: real-time speech-to-text plus a 27,000-word emotion lexicon and an AI expression analysis report. Runs offline - talk to it and it helps you spot the problems in how you express yourself.
The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.
LLMs as Copilots for Theorem Proving in Lean
A set of tools that gives agents powerful capabilities.
A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero human intervention.
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
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.
A lightweight self-hosted bot in a single binary, written in Go.
Daily updated LLM papers.
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.
A gooey, morphing toast component built on Sonner with Framer Motion animations
Tianshu is a harness-engineered terminal coding agent runtime (TUI x GUI) with deep prefix-cache optimization for DeepSeek V4 (97-99% steady-state hit rate measured in long sessions). It moves beyond treating the LLM as a mere "tool", building on a Cognitive Virtual Machine (CVM), a self-awareness layer, and Stigmergy-based decaying memory to make the AI a "development partner" with independent judgment and cognitive safeguards.
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
The most complete learning path for AI Agent engineers: 20 stages, 503 lessons, full Chinese translation, a companion site and animated explainer videos - a complete guide to becoming an AI Agent engineer.
X导师.skill — 女娲的第一个「非人类」作品。蒸馏6位顶级X创作者方法论 + 开源算法数据,提炼完整的选题-写作-增长操作手册。Made with 女娲.skill