Havuz

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-cha

One TypeScript API for running code in sandboxes. Write it once, run it on E2B, Daytona, Vercel Sandbox, Upstash Box, Railway, Tenki, Freest

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

Agent-first slide decks: comment under a slide, and your coding agent (Claude Code or Codex) makes the change and replies on the slide.

The Agentic-Native Operating System

Remote coding harness exposed as a secure Streamable HTTP MCP server

Amplify yourself and your team – with AI co-workers.

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

Local IMAP/SMTP bridge for Tuta encrypted email. Use Thunderbird, Apple Mail or any mail client. Rust + Tauri, with backup and search.

Application hosting made easy. Push a repo, pick a server, get a deployment - on any hosting, with any price.

Help your agent remember what matters. Keep preferences, carry context across sessions, and bring your memory to the next agent.

User-owned capability host for Aru: paired devices, computer collaborators, MCP, plugins, jobs and encrypted backup.

dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and h

GPT Image 2 (official) API (`gpt-image-2-official`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart

Code Buster reports dependency wiring, dead code, cycles, duplication, complexity, architecture-policy violations, feature flags, security a

리버스 Nano Banana Ext API: 1K $0.0125. model ID `gemini-2.5-flash-image-preview`, OpenAI-compatible, async task + cost in every response, $1 m

Runs, traces, tool calls, LLM calls, errors, latency, tokens, and eventually detection for agents that appear stuck or caught in loops.

Multi-tenant LLM API gateway for Claude and Codex — single Go binary, USD wallet, Alipay top-up, per-token caps, status-page health, fumadoc

Free HTTP/SOCKS proxies with every check on the record: passed, failed or couldn't run, and when. Hourly list, --pick --verify, --diagnose,

реверс-инжиниринг Grok Imagine 1.5 Ext API: 1K $0.015. model ID `grok-imagine-1.5-apimart`, OpenAI-compatible, async task + cost in every re

rétro-ingénierie GPT-Image-2 Ext API: 1K $0.0085; 2K $0.014; 4K $0.021. model ID `gpt-image-2`, OpenAI-compatible, async task + cost in ever

Hermes Agent context engine: the main model writes the compaction handoff on its cached prompt prefix

Architecture-first Codex skill for open-model behavioral interventions on dual DGX Spark

Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

rétro-ingénierie Nano Banana Pro Ext API: 1K $0.03; 4K $0.04. model ID `gemini-3-pro-image-preview`, OpenAI-compatible, async task + cost in

面向电商视觉生产的 Agent 技能库：26 个可组合的 skill.md，覆盖平铺图 → 模特上身 → 裂变套图 → 详情页 → 主图视频 → 投前质检 → 平台合规校验。不锁后端，dLazy / OpenAI / Gemini / fal / Replicate / 火山方舟

An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engin

I gave Claude Code 120 pages of my handwritten college notes. It gave me back my handwriting as a real font, in 66 minutes for $13.68.

Chat with local and cloud AI

A multi-agent Dynamic Island for AI coding on macOS, with a lighter Windows edition. Track Codex, Claude Code, DSH and Kimi Code on both; ma

Nexus — execution infrastructure for AI agents. Host agents in the cloud or behind NAT; let users attach and authorize their own computers a

Edge TTS voice plugin for DeepSeek Harness: read assistant replies aloud, auto-read toggle, voice settings panel (free, no API key)

Steerable, resumable, bounded-memory MiniMax H3 video workflows for ComfyUI

Open-source RDP server for macOS. Use your Mac mini or Mac Studio from a MacBook, Windows, iPad or Linux with stock Windows App, mstsc or Fr

A cache-aware attention and forgetting layer for high-frequency everyday AI chat.

Open-source, AI-native social media management, design & scheduling platform for 45+ channels. BYOK AI across 30+ providers with governance

Simulator-free, headless SwiftUI checks for AI coding agents: render screens as accessibility trees and hot-reload views in ~2 s, without th

本地电子书阅读器，以「听读」为核心。EPUB / PDF / TXT / MOBI / AZW3，任意倍速不变调，可导出 MP3 离线听。Local e-book reader with listen-and-read: EPUB, PDF, TXT, MOBI, AZW3.

Find the best AI models you can run

JsOwl —— Go 编写的 Web 安全信息收集利器。集 JavaScript 信息收集、API 端点提取、敏感信息扫描、攻击面梳理 于一体，同时提供 CLI 工具与 Go 库。内置 direct / browser / auto 三种采集模式，兼容 HaE 规则，支持登录态

文件化经验库：让 AI agent 不再重复踩同一个坑。方法论 + 模板 + 可选工具。

Hermes Bot — a native Mac interface to the Hermes agents you already have.

Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester t

AI-powered multi-model workspace and routing system for Claude, Codex and other LLM agents. Provides intelligent prompt routing, agent orche

Architecture search beyond the search space: an LLM writes architecture programs, population-based evolution decides which survive. Referenc

斯坦福 CS329Z《Engineering AI Agents》中文学习站 · 35 篇论文逐段中英对照全译(2035 段/45 万字)+ 14 篇博客规范全译 + 讲义同步 | 在线阅读 cs.xuyili.com

TLA+ model checking and Lean proofs for coding agents, with explicit tool setup.

Wan 2.7 R2V prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-r2v`) and the cost per image.

A fast, real-time multi-agent stock research and paper-trading platform.

开源 Agent Skill：一键部署 QQ AI 群友（AstrBot + NapCatQQ 全自动安装配置）