Havuz

一个人格 AI Skill 实验：别人垂直赛道，我垂直人格。

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

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

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。

The last harness you'll ever need.

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~

AI-native publishing system — build books like software. 6-phase pipeline from blank page to EPUB/PDF, with 16 skills, 7 agents, and 8 genre

Click does not replace Nx, Bazel, pytest, or Jest. It sits above existing verification tools and manages which verification evidence remains

Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind

AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL

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

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

GJC(Gajae Code) 5구독 멀티벤더 셋업 — 3대 리서치(Codex/LLM Council/Opus ultracode) + 엔진 ground-truth + red-team 통합 가이드

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

The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.

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

Task-plan driven SEO and LLM-friendly website skill cluster

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

Framework for building continuous-loop autonomous AI agents.

The open-source cloud for the agentic era. Don't pick a database, a region, or a RAM slider - your coding agent and Bay decide, then keep th

Langfuse on GreptimeDB. Self-hosted LLM observability.

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

Dark, lime-accented one-page portfolio of Bharani Kumar S — an AI full-stack developer. Smooth-scrolling vanilla JS, SEO-ready, Resend conta

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records,

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached di

How much code did AI actually write? Down to every line. Unifies 15+ tools, 600+ model pricing, one-command weekly reports.

A very fast, feature-packed, AI-first Markdown (CommonMark/GFM) gem for Ruby, based on pulldown-cmark (Rust).

Self-host AI companion platform — characters with schedules, memory, and a life of their own (BSL 1.1)

AI-powered code review agent for GitHub pull requests. Self-hosted GitHub App using PI.

Evidence-grounded market research prototype with traceable AI workflows.

Proof-driven Claude/Codex agent loop with paired execution, persistent resume, and adversarial security/performance gates.

Stop your AI coding agent from reinventing the wheel. A Claude Skill that checks Free vs. Build vs. Buy before writing code, and actually ve

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from

리설주 1.0 - 북한 AI

A high-performance, local, offline-first AI memory system built in Rust

Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.

AntNest 是一个采用蚁后 / 工蚁架构（或蜂后 / 工蜂）的 AI 编程助手。你可以把它想象成一个蚁群： 蚁后（本体）：只负责思考、规划、决策。蚁后从不亲自执行任何命令。 工蚁（复制体）：蚁后需要干活时，会生成一只工蚁——把自身代码复制一份，派到隔离的临时目录里执行命令。

NullFlux — 本地部署的中文 CFD / 科学计算智能体（OpenFOAM · MFIX · LBM · ParaView · 视觉核验 · 论文复现），by LZF

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

One native macOS supervisor for every local development server.

Multilingual source-grounded research workspace with agentic RAG, cited chat, podcasts, PowerPoint, and video.

ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-au

Agent-native disposable email — Cloudflare Workers + Durable Objects, with CLI & MCP. https://smails.dev

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

Free, portable AI agent skills and plugins for Codex, Claude Code, and Agent Skills clients by Slopware Engineer (@aienginerd). Home of the

Claude Desktop .mcpb bundle for Upvote.club. Part of upvoteclub/upvote-club-mcp-* family — see core repo for all packages.

The Humanness Index: the open benchmark for how human voice AI sounds, built by Vapi. Blind same-voice battles, pure-vote Elo, with a real-h

Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.