Skip to main content

Unified local GUI that drives attune-ai, attune-rag, and attune-author Python libraries via a FastAPI sidecar.

Project description

attune-gui

Unified local GUI that drives the attune-* Python libraries (attune-ai, attune-rag, attune-author, attune-help) through a FastAPI sidecar and a React + Vite UI. Designed so you don't have to remember CLI flags, MCP tool names, or sub-command paths to run common developer-workflow tasks.

What it does

  • Commands mode — run any of the 24 registered commands (RAG queries, doc generation, security audits, code reviews, memory recall/capture, release prep, …) from a 3-column form-driven UI. Async jobs with live status, structured results, and re-run with one click.
  • Living Docs mode — proactively tracks documentation quality across three consumer personas (End User, Developer, Support). Scans your workspace, surfaces stale or low-quality docs, and gates releases on RAG faithfulness / accuracy thresholds.
  • Profiles — Developer, Author, or Support. Each filters the command list to what's relevant for that role.

Quickstart

pip install attune-gui
attune-gui
# Or pick a specific port:
attune-gui --port 8765

The sidecar binds to 127.0.0.1, opens your browser, and serves the React UI from inside the package. No external services required.

For dev work against a local checkout (HMR + faster iteration):

git clone https://github.com/Smart-AI-Memory/attune-gui
cd attune-gui
uv venv && uv pip install -e '.[dev]'
cd ui && npm install && cd ..
./scripts/dev.sh   # starts sidecar on :8765 + Vite dev on :5173

Architecture

┌──────────────────────────┐
│  React + Vite UI         │  ← served from package, or Vite dev (HMR)
│  (Commands | Living Docs)│
└──────────┬───────────────┘
           │  /api/*
┌──────────▼───────────────┐
│  FastAPI sidecar         │
│  127.0.0.1:8765          │
│  ├─ commands.py registry │
│  ├─ jobs.py              │
│  └─ routes/              │
│     rag, ai, author,     │
│     help, profile,       │
│     living_docs          │
└──────────┬───────────────┘
           │
┌──────────▼───────────────┐
│  attune-rag, attune-ai,  │
│  attune-author,          │
│  attune-help             │
└──────────────────────────┘

Security notes

This is a single-user, local-only app. Not designed for multi-user deployment, not hardened against a motivated attacker on the same machine.

  • Binds only to 127.0.0.1 — not reachable from other machines
  • An Origin header guard rejects browser requests from non-localhost origins
  • Mutating endpoints require the X-Attune-Client header to match a per-process token (served from /api/session/token)

Related packages

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

attune_gui-0.1.0.tar.gz (113.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

attune_gui-0.1.0-py3-none-any.whl (90.7 kB view details)

Uploaded Python 3

File details

Details for the file attune_gui-0.1.0.tar.gz.

File metadata

  • Download URL: attune_gui-0.1.0.tar.gz
  • Upload date:
  • Size: 113.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for attune_gui-0.1.0.tar.gz
Algorithm Hash digest
SHA256 f087763a68370d5e79a3ebd0d06444658eb0824db8d9b22f6e881a122730b16e
MD5 bfba20ef6a44d292239a7e1204468898
BLAKE2b-256 3337c47953646b7800d26f375d1b2afbb950174e89896e39c8d6a54109643fbe

See more details on using hashes here.

File details

Details for the file attune_gui-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: attune_gui-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 90.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for attune_gui-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c95c71039d2c078dc8a86e9b90b0f67f4163473b417f0f0702383d00dba2f9b5
MD5 f28040dea7a312a91a7c376fb176c76f
BLAKE2b-256 b15e4ae5981badcad20358e64c218be8ba5b367c289bc17219a90852bc342b11

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page