CZ

chrispybiscuit/zen-harness

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

0 stars 0 forks 品質 68 トレンド 20Apache-2.0

Experimental private AI agent for Windows: runs Ternary Bonsai 2 27B on an 8-16 GB NVIDIA, AMD or Intel GPU, with tools, a planning harness, a REST API and MCP. Apache 2.0.

概要

Zazen is an early alpha from a small independent project. It runs commands and edits files on your PC (it asks before risky steps), its AI makes mistakes, and settings, file formats and features can change without notice. Use it on files you have backed up, review what it builds, and don't rely on it for anything important. Zazen is a desktop app that runs a capable open model, Ternary Bonsai 2 27B, on an ordinary 8 GB graphics card, and gives it tools: files, a terminal, web search, a browser, offline Wikipedia, documents, and code it can test. Your chats and files stay on your computer. Status: . It works, and it has rough edges. See What it can and can't do. - People who want an AI assistant that works , with no account, no subscription and no telemetry. - Developers and tinkerers who want a for small apps, scripts, data jobs and fixes in their own projects. - Anyone with a gaming PC or laptop who wants to use its graphics card for more than games.

README

以下は原文 README の抜粋です。原文を見る。

Zazen

[!WARNING] Experimental software. Zazen is an early alpha from a small independent project. It runs commands and edits files on your PC (it asks before risky steps), its AI makes mistakes, and settings, file formats and features can change without notice. Use it on files you have backed up, review what it builds, and don’t rely on it for anything important.

A private AI agent that runs on your own Windows PC. Zazen is a desktop app that runs a capable open model, Ternary Bonsai 2 27B, on an ordinary 8 GB graphics card, and gives it tools: files, a terminal, web search, a browser, offline Wikipedia, documents, and code it can test. Your chats and files stay on your computer.

Status: experimental alpha. It works, and it has rough edges. See What it can and can’t do.

Who it’s for

  • People who want an AI assistant that works offline and privately, with no account, no subscription and no telemetry.
  • Developers and tinkerers who want a local coding agent for small apps, scripts, data jobs and fixes in their own projects.
  • Anyone with a gaming PC or laptop who wants to use its graphics card for more than games.

It is not built for teams, servers, or work that has to be right the first time without review.

What it was designed for

Small local models get lost on long tasks: they forget the goal, repeat themselves, and say “done” when it isn’t. Zazen is a harness built around that problem, tuned on a real 8 GB laptop:

  • A plan and a checklist for every larger task, kept in view as the work goes on.
  • Proof before “done”: code changes need a passing test run, and a program it built must actually start (a page loads without errors, a server answers) before the agent may call it finished.
  • Loop guards: repeated identical actions are caught and the agent is told how to get unstuck.
  • Context management for slow models: older steps are compacted into short structured notes, so a 1-bit 27B model can work for hours on a 60K-token window.
  • Hardware detection: it finds your graphics card and sets up the model, runtime and memory settings for it.

What it runs on

Requirement
Operating system Windows 10 (22H2) or 11, 64-bit
Graphics card A dedicated card with 8 GB or more of video memory, up to 16 GB supported
Memory (RAM) 16 GB
Disk About 10 GB: the app, the GPU runtime (30–700 MB), the model (5.9 or 7.2 GB). Offline Wikipedia adds 14 GB (optional).

Graphics cards:

Vendor Status
NVIDIA GeForce RTX, 8 GB+ Supported and tested (RTX 3070 Laptop, 8 GB)
AMD Radeon, 8 GB+ Supported, not yet tested on real hardware
Intel Arc (8 GB+) Supported, not yet tested on real hardware
Under 8 GB, integrated graphics, no GPU Runs on the CPU, very slowly: not a supported setup

The app picks the runtime for your card (CUDA, HIP, Vulkan or SYCL builds of

GitHub で README 全文を見る

インストール

This server does not publish a one-line install command.

Open the repository installation guide MCP 初心者?mcpskill.org のガイドから始めましょう →