Havuz

리버스 GPT-Image-2.5 Ext API: 1K $0.0085; 2K $0.014; 4K $0.021. model ID `gpt-image-2.5-ext`, OpenAI-compatible, async task + cost in every res

리버스 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 every response, $

霓虹天頂 — a rain-soaked vertical cyberpunk city you can fly through in the browser. three.js WebGPU + TSL, a Blender-baked Hong Kong night mark

Agent 式的 SillyTavern 角色卡酒馆：高缓存命中，兼容酒馆角色卡与世界书，自带配图和一键朗读，角色形象固定，引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.

ArcGIS Pro add-in that speaks the Model Context Protocol, so an AI assistant can drive your open project in plain language — 112 tools, ever

Автоотклики на hh.ru: письмо под каждую вакансию, ответы на анкеты и анализ резюме нейросетью, отказы и приглашения из чатов, подъём резюме

AI-assisted text editor for Windows with local LLM support, text rewriting, style improvement and Unicode cleanup.

Create Instagram Reels, TikToks and YouTube Shorts with adaptive AI editing, captions and motion graphics. Connect FavStash for planning, pu

Agent reliability rulebook: the threat model and rationale behind each Agent Reliability Analyzer rule

Codex 国内使用与报错速查：安装、登录、手机号验证、终端代理、断线重连、额度用完、上下文满了，以及接入 DeepSeek 等第三方 API。按报错原文查原因和处理步骤，每条附官方出处；含中英界面对照和 AGENTS.md 中文模板。

A CLI and MCP server for Things 3

Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

Open the live page and check it against what you asked for. SHIP, FIX, or CAN'T SEE. Then patch only the named misses. Stop agents shipping

Your Claude Code agents, living in a tiny pixel-art office. Desktop widget + browser app, with tokens, a shop and a lounge.

A self-hosted LINE assistant for notes, reminders, file storage, and hybrid search.

AI and IoT-based plant monitoring system with sensor monitoring and a Telegram chatbot.

UI/UX and frontend design skill for AI coding agents: Codex, Claude Code, Cursor. Art direction, DESIGN.md, design tokens, motion, accessibi

The settlement day for everything you subscribe to — a self-hosted, AI-native subscription ledger with multi-currency, shared plans, reminde

把你的手机变成 AI 手机：一个住在手机里的 Personal Agent，交代一句就替你办好。Turn your phone into an AI phone.

FLUX 2 Pro prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`flux-2-pro`) and the cost per image.

Always-on durable pi agent on your server that you talk to in Telegram. Survives crashes and restarts, keeps history in SQLite. pi-durable T

Grok Imagine 2.0 API (`grok-imagine-2.0-ext`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpo

Reclaim disk space with an AI agent: measure top-down, group findings by risk, and delete only what you approve. Prompts in 7 languages. mac

Portable AI agent skills, subagents, and plugins for architecture/AEC workflows across Codex, Claude Code, Gemini CLI, and other compatible

Free up storage on a Samsung Tizen TV when Delete is greyed out. Honest guide to what sdb can and cannot do on retail firmware — includes a

Open Source Ahrefs & SEMrush

Free, open source dictation for Mac. A Wispr Flow alternative that runs offline and grows with TypeScript extensions.

Control your real browser and ScriptCat from the CLI, AI clients (MCP) and scripts: tabs, browser data, page automation, debugging, raw CDP,

Open-source Blender AI add-on and MCP server for prompt-based 3D modeling, scene generation, Edit Mode changes, reference images, viewport s

Free, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.

High-performance Git alternative for AI agents with instant (<30ms) virtual workspaces and AST merge. Inspired by Google CitC and Anthropic

Coding Tools MCP, MCP üzerinden AI istemcilerine bir çalışma alanında dosya, komut ve Git araçları sunan bir coding runtime'dır.

Neden yükseliyor · 130 günlük yaşına göre 1154 yıldız, ortak ve modelden bağımsız MCP coding araçlarına ilgi olduğunu gösteriyor. Ancak son 28 günde 2 commit ve 2 farklı yazar var; bu nedenle güncel geliştirme temposu veya yaygın kullanım hakkında güçlü kanıt sayılmaz.

SiliconScope, Apple Silicon Mac’lerde sistem kaynaklarını ve özel hızlandırıcıları izleyen, ayrıca uzaktaki makineleri aynı panele ekleyebilen bir macOS monitörüdür.

Neden yükseliyor · 111 günde 966 yıldıza ulaşması ve son 28 günde 48 commit alması dikkat çekiyor; README’deki ANE ve memory-bandwidth ölçümleriyle uzaktaki makineleri tek panelde toplama özellikleri de ayırt edici bir kullanım vaadi sunuyor. Üç farklı yazar aktiviteye işaret etse de ekip genişliği sınırlı; yıldızlar tek başına benimseme veya kalite kanıtı değil.

otelyssey, OpenTelemetry odaklı agent plugin’lerini listeleyen ve gönderimlerini repository üzerinden doğrulayıp takip eden bir marketplace sunuyor.

Neden yükseliyor · 8 günlük yaşına rağmen 65 yıldız ve son 28 günde 87 commit almış. Bu görünürlük, coding agent’lara yönelik plugin ekosistemi ile OpenTelemetry ilgisinin kesişmesine bağlanabilir; ancak commit’lerin yalnızca 2 farklı yazardan gelmesi, hareketliliğin geniş topluluk katkısı anlamına geldiğini göstermiyor.

Astra Flash Orchestrator, Codex veya OpenCode iş akışında planlama ve son incelemeyi Astra'ya, uygulama ve test döngüsünü DeepSeek V4.1 Flash'a devreden bir geliştirme aracıdır.

Neden yükseliyor · 11 günlük yaşına karşılık 694 yıldız ve son 28 günde 14 commit görünür ilgiye işaret ediyor. Ancak bu metrikler, benimsenmeyi veya iddia edilen tasarrufları doğrulamıyor; README'nin erken sürüm uyarısı ve yalnızca tek yerel saha çalışmasına dayanan ölçümü dikkate alınmalı.

On-device, real-time multimodal AI with features similar to GPT-Live

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic m

Codex for Android, iOS & Mac. | Aether 扶摇

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No

Emergence World: A world designed to reveal what no benchmark can: emergent intelligence.

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

What if your phone had no apps

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, a

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub A

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from

ИИ-девушка с человеческим поведением: сон, настроение, расписание, память, стадии отношений и конфликты. Userbot mode через MTProto — реагир

Let AI agents investigate and operate infrastructure through declared actions, bounded by policy and host-side checks. Approvals when requir