muselab

agent
Guvenlik Denetimi
Basarisiz
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 13 GitHub stars
Code Basarisiz
  • fs module — File system access in .github/workflows/ci.yml
  • Hardcoded secret — Potential hardcoded credential in .github/workflows/ci.yml
  • network request — Outbound network request in backend/auth.py
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

your archive + Muse, the AI that actually knows you. Self-hosted, no npm, no bundler, no build step. Powered by Claude Agent SDK.

README.md

muselab

CI
License: MIT
Self-hosted
Container
中文

Muse (muselab's built-in assistant) reads across your checkup PDFs, budget spreadsheets,
family info, asset allocations, and career plans — helping you make cross-domain decisions.

  • 🧠 Raw semantics, zero loss. No vectorizing. PDFs, spreadsheets, Markdown, HTML —
    the original information stays intact. Muse reads them directly. The richer your
    material, the better the outcome.

  • 🤖 Claude Agent SDK × eight models. MCP tools, Skills, Subagents, plan mode — all
    intact. Not just chat, real delivery. Claude / DeepSeek / GLM / MiniMax / Kimi /
    Qwen / MiMo / ERNIE — switch in one click.

  • 🖥️ Live rendering, multi-device sync. Muse's HTML reports and Markdown docs render
    live in the preview pane. Sessions sync across desktop and phone, with PWA install
    and push notifications.

muselab desktop: file tree, chat, and a live-rendered preview pane    muselab on a phone — the same session, continued

Rich rendering, real-time multi-device sync — HTML reports, tables and charts render as they're written; one session shared across desktop and phone.

See it in action

🌐 muselab promo page
scene demos, capabilities overview, comparisons & FAQ — a quick look at what muselab can do.

Install

Prerequisites: git, curl (bundled on Linux / macOS; on WSL2 run sudo apt install git curl).

One-line (Linux + macOS + WSL2) — installs uv, clones into ~/muselab,
then runs the platform installer (which auto-installs Node LTS + the Anthropic
claude CLI and registers the service):

curl -fsSL https://raw.githubusercontent.com/hesorchen/muselab/main/scripts/quick-install.sh | bash

Windows users: install via WSL2 (see Quick start).

Unattended — for CI / Docker / demo recording. Takes every default
(random token, port 8765, ~/muselab-archive) and skips every prompt:

curl -fsSL https://raw.githubusercontent.com/hesorchen/muselab/main/scripts/quick-install.sh | MUSELAB_NONINTERACTIVE=1 bash

Manual — if you'd rather see every step:

git clone https://github.com/hesorchen/muselab && cd muselab
bash scripts/install-linux.sh    # or install-macos.sh

Open http://localhost:8765, paste the token from .env. If the installer
reported "claude CLI is installed but not logged in", run claude login
once to enable Anthropic models.

For prerequisites, Docker, dev mode and per-OS detail, see
Quick start.

Docs

📚 Full documentation index

Status

v1.0 — first stable release. PRs are welcome — see CONTRIBUTING.md.
The roadmap and known issues are tracked on GitHub Issues.

MIT

Yorumlar (0)

Sonuc bulunamadi