Havuz

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Thinking in the Human · Processing in the AI · Truth in the Documentation

Очеловечить текст нейросети: убирает длинное тире, канцелярит и штампы ChatGPT, не трогая факты. Правила для любой нейросети + скилл для Cla

Open-source AI coding agent for your terminal, written in Rust. One 7 MB native binary for Apple Silicon Macs, ~18 MB RAM, 70–90% prompt-cac

AI code review that lands on the PR, not in your terminal — GitHub, GitLab, Bitbucket. Learns each repo's conventions: 1 review, 1 fix commi

Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.

The next easy code and work AI agents harness system: auto, asynchronous, concurrency, efficiently and High accuracy

Open database of system prompts extracted from frontier LLMs using JustAsk

Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qw

CareerDesk: Your Personal Career Assistant

Wavelet-based multi-resolution context management for LLMs via MCP

由 LLM 驱动的可交互智能体：有记忆、有性格、有自己的日程与作息

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside

An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harnes

Open-source agentic infrastructure & alternative to Grok Bot. Bring Claude Code, Codex, OpenClaw or your own. Start without building from sc

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

🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8

Offline-first Go CLI for engineering teams to observe AI adoption, compare estimated coding-tool costs and inspect bounded local delivery ev

Vibe Mathematics —— 多代理数学问题求解与形式化验证框架

MCP-сервер для 1С:Предприятие через OData: данные 1С на естественном языке из любого MCP-клиента (Claude, Cursor, VS Code, локальные модели)

WorkBuddy Multi-Account Manager & Automated Check-in Toolkit (多账号轮换、全域工作区打通与自动化签到)

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

A general-purpose terminal AI agent with traceable knowledge sharing and dispute resolution｜面向终端的通用 AI 助手，可独立运行或参与团队协作，让 Agent 共享可检索、可追溯的知识，

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

📰 An automated, multi-agent research ops AI pipeline that gathers daily AI news, synthesizes it into structured briefings, and delivers them

Unofficial MCP server for T-Bank (Т-Банк, ex-Tinkoff) mobile banking: accounts, cards, transfers, bill pay, grocery ordering, tickets & trav

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)

✨✅ The easiest decisions your code will ever make.

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

The AI Runtime for Kubernetes

Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsur

基于用户意图进化的智能 Agent 助手平台，目前主要支持文件解析、Excel 数据分析、合同审查、知识库检索、报告导出与自定义技能。

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

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering,

Open-source AI chatbot & site search for your docs. One <script> tag, streaming answers with sources. 100% Cloudflare-native (Workers AI + V

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

BOAR - Adaptive Local Intelligence

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Cut Claude Code costs with sourced levers -- prompt caching, model routing, Batch -- plus an installable skill, CLI tools, a cost calculator

Local-first workspace token calculator and model recommender for coding agents, with repo maps, VS Code, CLI, and MCP.

A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S), f

1-Click Grok Bot 8 Man Crypto Trading Desk as seen on X

A self-hosted app that turns RSS feeds into conversational podcasts for commutes. 将 RSS 转成对话式播客，让通勤成为轻松获取信息的时刻。

Spatial prompt engineering through interactive 3D concept graphs

Store every accomplishment. Tailor every application. Own your career data.

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

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

Lightweight proxy for LLM