Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
FAQ
LLM apps, prompts, RAG, embeddings, model gateways, inference utilities.
Specializations
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.
CodeAlchemist: Distills a developer's coding style, architecture preferences and engineering patterns from Git commit history into a reusable Claude Code Skill. CodeAlchemist:从 Git commit 历史中系统提炼开发者的代码风格、架构偏好与工程模式,并固化为可复用的 Claude Code Skill。
Zero-token diagnostic engine for upgrading Claude Code skills to Skills 2.0 compliance
Claude Code skill that removes signs of AI-generated writing from Russian text. Russian adaptation of blader/humanizer with ~38 patterns specific to Russian: канцелярит, родительные цепочки, «является», кальки, типографика.
Claude Code skill for SageMaker LLM training (SFT, LoRA, QLoRA, DPO, CPT)
TESS NG 二次开发Skills, 遵循Claude code Skills标准
Reverse-engineer any author's writing style from samples, then write in their voice. 24-dimension forensic style analysis.
Agent Skills for on-device ML: FunctionGemma fine-tuning, LiteRT-LM export, and more. Compatible with Claude Code, Codex, and Gemini CLI.
ຄຳລາວ — Lao language quality + compression mode for Claude
Turn any GitHub repo into an agent skill. Make any open-source repo an agent's claw. 🐾
Resources for fine-tuning Claude Code for my development practices. Includes CLAUDE.md global and local templates, claude skills, claude subagents.
Karpathy-style LLM wiki pattern as Claude Code skills (research-wiki + meeting-progress) for maintaining a compounding knowledge base over accumulating progress reports.
A Claude Code skill for fine-tuning LLMs using Red Hat training-hub.
Claude Code Skills for NovaCustomization SDK
✨ 管好 Claude Code 的一整套记忆机制 —— CLAUDE.md · auto-memory · .claude/rules · 磁盘,自动生成 / 体检 / 进化,不用手写不惦记维护
Atelier — autonomous design agent for the Google for Startups AI Agents Challenge 2026. Stitch generates. Atelier asks, converges, learns.
Parallel code implementation skill for Claude Code. Spawns up to 5 concurrent agents with git worktree isolation, auto-retry, and structured review. /delegate [task]
A Claude skill that enforces citation-first research discipline. Classifies claims, verifies before writing, signals confidence levels, and audits output for hallucinations. Works with Claude.ai, Claude Code, Cursor, Codex, and Gemini CLI.
AI Studio 无代码大模型微调 Skill,一句话触发,全程引导,支持 ERNIE 和 Qwen/LLaMA
An MCP server for dataset generation, fine-tuning, RL, and evaluation of LLMs — directly from your coding agent.
A Claude skill that removes visible AI-tells from finished work. Polish handles em-dashes, hollow phrasing, and small inconsistencies across prose, code, UI, and slides. Strict rules where it matters, contextual judgment where genre decides, and memory of how you like things done.
Convert Claude Code Skills into IBM Bob Skills.