Havuz

Local-first AI agents for your Obsidian vault.

🔒 Local, free (no ads) optimization co-pilot for the idle-RPG TBH: Task Bar Hero — reads your save in-browser and tells you the optimal next

把整套 Agent 体系装进口袋：本地优先的 Android 小说创作应用。智能体可读写你的章节、角色与世界书，参考文风能蒸馏、你的修改会被学习；作品数据全部留在手机，只有调用模型时才联网。基于 OpenFic 重构。

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

微信文章归档工具 - 本地Markdown保存 ｜ Archive WeChat Official Account articles as local Markdown for Obsidian, Logseq, and personal knowledge bases.

Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

Local-first privacy toolkit. Map yourself against 400+ data brokers, send CCPA/GDPR deletion mail, and check password dumps. The vault never

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

🪁 Read any manga in your language directly in-browser. 100% local-first AI translation with WebGPU OCR, clean background inpainting, and stu

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

Persistent code memory for AI coding agents, kept in your project on your machine. Gives Claude Code, Cursor, Cline, Hermes-Agent and any MC

Agentic development environment: run Claude Code, Codex, OpenCode and Gemini CLI side by side, and follow every PR from agent to release wit

Local-first git graph and session debugger for Claude Code, Codex, Cursor, OpenCode, and 7 more AI coding harnesses.

SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflo

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali

Local-first adaptive tutoring agent foundation reference implementation for iOS and Web, with a civil-service exam application.

Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail in the SIEM you alre

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。

Flint · local-skills-hub — a local-first personal AI skills asset manager. Centralize, tag, deduplicate skills, and deploy them into agent a

Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey,

Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.

Local-first MCP memory server for AI agents. Zero dependencies, SQLite on your own disk, 52 MCP tools with Mem0-compatible names. MIT.

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

与 Agent 共用一块画布：以画布为中心的 Agent 工作台。网站、演示稿、Word 文档、图像与视频集中在同一块画布上，用户指定、整理与修改，Agent 制作、检查与说明。支持 Windows 桌面版与自有密钥（BYOK）。

An open-source AI assistant for work and everyday life. Remembers context and helps you get things done. Local-first, on a computer you choo

Translate retro games with AI on your own computer: extract the text, translate, validate, reinsert and export a patch. GBA, NDS, NES, SNES,

Open source expense tracker, budget app, and subscription tracker for iPhone and Android. Local-first, built with Expo and Convex.

A Codex CLI plugin that grades how you collaborate with Codex across 9 dimensions in 3 categories — your Codex model writes a free-form diag

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/c

Synapse is a local-first, offline-first, installable PWA that unifies habit tracking, task management, workouts, finance, and more into a pr

Rebuild a local twin of your app on every push, replay approved business journeys, and report a GitHub check.

Open-source, AI-native research workbench for literature search, reading, knowledge management & academic writing. Connects papers, notes an

A visual editor for Mermaid diagrams — draw on a canvas, get Mermaid code. Local-first: no server, no accounts.

Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key)

A local terminal control plane for Codex, Claude Code, and pi sessions—discover, monitor, resume, and work beside persistent workspace shell

Browser-based Android console, APK decompiler and security analyzer. Mirror, logcat, shell, Frida, jadx, and static and dynamic analysis, wi

微信.skill: 让 AI 读懂你的微信

Local-first desktop app that turns reviewed Git history into auditable weekly reports with Codex, Claude Code, or your own model.

A local-first studio for roleplay and long-form writing: a roleplay chat with a living Narrative State, a Worldbuild that keeps your canon,

A native macOS desktop pet that visualizes OpenClaw agent activity.

Lydia is a local AI coding agent for the terminal. It reads and edits your code, runs commands, and drives git through a local Ollama model.

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

Local TTS voice mode for Claude Code with word highlighting and no cloud APIs.

privacy-first context graph engine for AI agents and human teams.

A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.

Install once, talk to your agent. ThinkWiki turns documents and notes into a local Markdown wiki with inbox review, content knowledge graph,