Havuz

Free and open-source production-grade RAG platform that converts documents into conversational AI assistants. Enable private deployment for

Turn a YouTube video or a web article into didactic study notes, rendered as a self-contained HTML page. Agent skill for Claude Code, Codex,

Your AI workspace for smarter conversations, creative tools, and powerful agents. Bring your favorite models together and make it your own.

Make Claude Code write plainly. A CLAUDE.md block plus the A/B harness that proves it works.

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek

目前数据支撑最扎实的中文公文写作 Skill：720 期笔杆子博主视频 + 5 本专著 + 27 份政府工作报告 → 蒸馏 965 条结构化知识（350 万字语料底账）。量化文风参数、GB/T 9704 国标 docx 排版、15 用例四轮评测验证——不是提示词堆砌，是蒸馏出来的

Interactive, animated architecture maps for any Hugging Face model — no weights downloaded

DeepSeek Harness 核心的便携引擎 + Termux 友好的终端编程 Agent CLI（pi 壳 + DSH 引擎，零运行时依赖，359MB→7.6MB 单文件）

Rakazo, kullanıcının seçtiği model ve bilgisayar sağlayıcısıyla web, masaüstü veya mobil üzerinden kalıcı AI teammate'ler çalıştırmasını sağlayan self-hosted bir platformdur.

Neden yükseliyor · 45 günde 2.978 yıldız, son 28 günde 448 commit ve 21 farklı yazar kayda değer ilgi ve geliştirme temposu gösteriyor. Kalıcı AI teammate'ler, self-hosting ve model/sandbox seçme esnekliğini tek üründe birleştirmesi dikkat çekiyor; yıldızların hangi kullanım veya benimseme düzeyine karşılık geldiği ise verilen verilerden anlaşılamıyor.

dsh-cost-meter, DeepSeek Harness için session bazlı maliyet, token kullanımı, bütçe ve çeşitli provider’ların quota bilgilerini gösteren bir plugin’dir.

Neden yükseliyor · 45 günlük yaşına rağmen son 28 günde 138 commit ve 12 farklı yazar katkısı, yüksek geliştirme temposuna işaret ediyor; 339 yıldız da erken dönemde ilgi gördüğünü gösteriyor. README’deki geniş özellik kapsamı dikkat çekici olsa da, kullanım veya benimsenme düzeyi hakkında ayrıca kanıt sunulmuyor.

Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub

1200+ AI models in your GitHub Copilot Chat — free & forever free. VS Code extension powered by OmniRoute: 340+ providers (90+ free) — Kimi,

HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI,

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency S

Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT.

AI-powered CLI for reviewing GitHub pull requests, detecting potential bugs, security risks, regressions, and missing tests, with structured

Trusted e-commerce AI after-sales platform — RAG, controlled tools, human confirmation, Java-authoritative writes, and observable workflows.

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

This repository provides a starter kit for sports intelligence built on NVIDIA AI stack: playbooks, training recipes, and inference for Mult

CliffCompaction — autocompaction for long-horizon coding agents

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compile

Self-hosted, distributed, multi-model LLM inference

Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)

Turn any YouTube video into a deck of timestamped knowledge cards. Runs locally, works with free models.

A free textbook on building an LLM inference stack from scratch in Rust.

闲鱼盯价助手：关键词监控 + AI 品相筛选 + 卖家信用 + 微信/企业微信推送（本地开源工具）

A lightweight, inspectable TypeScript coding agent for local software-engineering work.

DeepSeek Harness 中文 Windows 桌面版：女仆鲸桌宠、主题、插件市场、模型路由与安全更新。

iPad-first, open-source iOS AI Agent with native on-device 3D/CAD editing, iPhone support and Android alpha. On-device Linux, terminal, Pyth

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

已上架 Chrome / Edge 商店 🚀 把 B 站视频变成学习资源的浏览器扩展：字幕阅读、双语对照、AI 章节概览、划词解释和带时间戳的笔记

Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on

墨参 MoShen · 个人写作 Agent — 自整理资料、自核对设定、自追踪伏笔，但不代你动笔

让 AI 像人一样说话、创作的规则集。Ruleset for making AI talk and write like a human.

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

Static-analysis-based dataset for training LLMs to detect, explain, and patch security vulnerabilities (Java, Korean/English annotations, ve

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

Human as Agent（人即智能体）· Human-as-LLM 人工代理网关：把工程师变成模型，OpenAI 兼容 /v1 接入 Agent 调度池，涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gate

Local-first personal workspace: write notes, track tasks, chat with an AI that knows your files - all plain Markdown, no cloud.

A lightweight workflow orchestrator for Pi with six specialist agents for exploration, research, architecture, UI/UX, implementation, and v

Your AI coding agents keep working while you sleep. Drive Claude Code, Codex, Gemini, opencode & more from your phone: resume past usage lim

AI job-search scout: daily board sweeps, LLM triage, human-in-the-loop by design. It finds the jobs, you still have to apply!

MLOps — vLLM + LiteLLM + Portainer CE + Netdata. Case study song ngữ: kiến trúc, metrics, bài học vận hành. · Self-hosted LLM inference don

Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, a

AI SRE agent diagnosing Kubernetes incidents over Google Chat — security-first sandbox: NixOS VM, default-deny egress, hard tool denylist ag