Havuz

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

Turn dense long-form ideas into immersive Reading Editions.

Operational doctrine for practical AI systems design.

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

🚿 Llaminar: an LLM inferencing engine in C++.

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embedding

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven,

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence

Agent skill that audits and cleans agent-facing markdown docs — archives completed-work history, fixes stale facts and contradictions, keeps

One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server

C# MCP server for kernel & user-mode Windows debugging — DbgEng COM, KDNET, Frida, dbgsrv, TTD, and integrated VM control. 29 tools for LLM

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do li

Lint rules for your AI agent's discipline, not its code

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

DIO PRO Vitalício Week: Agentes de IA

Community benchmark database for running LLMs on Apple Silicon Macs

Open-source Claude skills and an MCP server for Sales and GTM teams: build Sales Navigator searches, write multichannel campaigns, and handl

A terminal-first ADE for the coding agents you already use: real PTYs, git worktrees, diffs and pull requests in one window

RepoPilot AI is a single-page web application that uses AI to analyze GitHub repositories and provide instant insights into architecture, te

Turn your AI coding agent into a tutor. It learns your level and adapts to you

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable

A family of small protocols for the perceptual side of designer-agent collaboration.

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

Perhaps the only agent skill you need: if memory loss is the root, let every AI agent rebirth follow the First-Time Principle. That's all.

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Papers in, ideas out. Generate research, product, or feature ideas from 250M+ academic papers.

The visual layer of your agent harness. Renders React components and Three.js scenes from source, with structure and evidence behind every f

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted,

Evidence-driven production readiness checklist for shipping web applications with confidence

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 1

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

高级朦胧梦幻动态视觉 Skill：把随手拍照片转化为电影感图生图提示词。Dreamy motion editorial prompts from casual photos.

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to

Alcove-style dynamic notch for T3 Code: live agent progress, task lists, and approvals answered under the Mac notch

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

🐙 Admin console for the OCTO platform — manage tenants, users, spaces, channels, and Lobster agents. Built with React, TypeScript, Vite & An

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to pre

Build UI apps with your AI assistant — together, live. An agent-native, cross-platform declarative-UI runtime in Go: describe UI as JSON, le

A terminal AI that doesn't babysit you. sot-cli gives LLMs full power, a novel memory architecture that slashes token costs, and agent orche

AI agent skill bundle for Storybook on React + Vite — audit real-vs-slop components, capture flows, write CSF3 stories, ship. Claude Code /

Langfuse on GreptimeDB. Self-hosted LLM observability.