ginno

mcp
Security Audit
Pass
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 10 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Local-first personal AI agent desktop app — Claude Code's shape with a visual workflow studio, local knowledge base, and zero cloud. Tauri + Next.js + Python.

README.md

Ginno

A local-first personal AI agent that runs on your own machine.

The shape of Claude Code, all-file storage (no DB · no account · no cloud), and a visual Workflow Studio.

License: MIT
CI
codecov
Platform
No cloud

English · 简体中文

Ginno chat workspace


What it is

Ginno turns the capabilities an AI agent should have into a complete desktop app,
instead of scattering them across a terminal and a dozen browser tabs.

  • 🧠 Multi-agent chat — switch agents mid-conversation, shared history, per-agent memory
  • 🛠️ Tools · permissions · skills · MCP · hooks — Claude Code's shape, all built in
  • 🔀 Visual Workflow Studio — a versioned DSL you compile into a LangGraph state graph, with a live run observer
  • 📚 Local knowledge base — index your Obsidian vault; answers come back with citations
  • 🎯 Long-horizon goals + TODO sync — let the agent keep working toward a standing objective
  • 🌐 Embedded browser + web search — retrieval with source attribution, not vibes

Full feature walkthrough: docs/user-guide.md.

Workflow Studio Local knowledge base
Workflow Studio Knowledge base

Why "local-first"

One design rule: your data should not leave your machine.

Ginno
Database ❌ none — all state is JSON / JSONL / Markdown under ~/.ginno/
Account ❌ none — open it and go
Cloud sync ❌ none — everything stays local
Portable ✅ copy the folder to move it; readable, hand-editable, git-able

You bring your own model key (OpenAI / Anthropic / DeepSeek, or any compatible endpoint).
Ginno is just a client — it never takes custody of your key or your data.


Install

Option A — download (macOS, Apple Silicon): grab the latest .dmg from
Releases.
It is not code-signed yet, so on first launch use right-click → Open to get past Gatekeeper.

Option B — build from source:

git clone https://github.com/robscc/ginno
cd ginno

pnpm install                       # web + desktop shell
cd packages/runtime && uv sync     # Python runtime
cd ../..

pnpm dev                           # web + runtime + desktop shell, all at once

Requires: Node ≥ 20 · pnpm ≥ 9 · Python ≥ 3.11 (via uv) · Rust (Tauri).

Package a .app: make app → apps/desktop/target/release/bundle/dmg/Ginno_*.dmg
(see docs/p3-packaging-notes.md).


Stack

Layer Choice
Shell Tauri 2 (Rust) — process management + webview only
UI Next.js 14 (static export) + React 18 + Tailwind
Runtime Python + FastAPI + LangGraph (sidecar, bundled with PyInstaller)
Storage plain files (no DB); optional LanceDB for semantic-search vectors

Architecture and subsystem designs: docs/architecture.md.


Documentation

User guide full walkthrough of every feature
FAQ · Troubleshooting common questions · known failure modes & fixes
Upgrade guide moving between versions — your ~/.ginno data survives
How it compares vs Claude Code / Cline / Open WebUI / LangGraph Studio
ROADMAP · CHANGELOG where it's heading · what shipped
CONTRIBUTING · SECURITY dev setup, testing, release runbook · vulnerability disclosure

Status

  • A personal project, used daily (dogfooding) and iterated fast — ~2.5 months, 220+ commits.
  • Early and unpolished; APIs and UI still move.
  • Issues, PRs, and ideas are welcome — in English or Chinese (see CONTRIBUTING).

License

MIT © 2026 ChuanchuanSong

Reviews (0)

No results found