The open-source home for
all your Claude Code
A self-hosted web UI that runs every Claude Code session on your laptop and your remote dev boxes from one console — streaming every tool call live, with a GitHub-style review of exactly what each session changed. Plus tasks, notes, and a memory that organizes itself. Your data stays on your machine.
One app for everything around Claude Code
Stop losing sessions in terminal tabs. Walnut gives Claude Code a real UI and ties it to the work it's for.
One console, every machine
Add a hosts: block to your config and one Walnut console drives Claude Code on your laptop and every remote dev box over SSH. Walnut works with your node manager (nvm / fnm / volta / asdf) and deploys its own daemon — gzipped and chunked so it survives corporate proxies, no manual scp. Terminal, file browser, the command & skill palettes, and the diff view all work over SSH exactly like local.
Sessions are resilient: if the tunnel or daemon dies, the remote daemon adopts and reconciles the still-running claude -p processes on restart — the remote session log is the source of truth, so nothing is lost.
Natural language → task → live session
Tell the main agent what you want. It creates the task and spawns a Claude Code session for it — in one shot — then streams every tool call and output live in your browser.
A real session panel
Chat with the session and switch modes like the CLI, open a real terminal, browse files, recap past messages, or fork into a sub-session — all in one click.
Focus, Satellite, Wait
Drag what you're actively working on into Focus, park secondary work in Satellite, and hold blocked work in Wait. Status is color-coded and updates as the AI works.
Tasks, agent chat & Claude Code — one screen
Tasks on the left, the main agent chat in the middle, your live Claude Code session on the right. The agent manages it all with full context from your memory and notes.
Notes & memory the AI can search
An Obsidian-style notes vault stored locally and indexed in a local vector database. Ask "what is my health routine?" and the agent finds it across your notes — nothing leaves your disk.
🖥️ Multi-session dashboard
Run and monitor dozens of Claude Code sessions side by side, with live status, mid-session model switching, and plan → execute.
✅ Tasks that drive sessions
A 4-layer Category → Project → Task → Subtask hierarchy with priorities, due dates, dependencies, and tags — each task wired to its Claude Code session.
🧠 Self-organizing memory
Working memory updates as you go, and a background agent distills daily logs into searchable topic pages — recency-weighted, hybrid BM25 + vector search.
📓 Notes the AI can search
Obsidian-style markdown with [[wiki-links]], backlinks, a folder tree, and hybrid search — injected into every session as context.
💬 Multi-conversation agents
Create on-demand agents, each with independent fresh-context conversations; what you discuss is auto-distilled into that agent's memory.
⚙️ Cron & automation
One-time, interval, and cron-expression jobs with timezones, heartbeat checklists, and automated session triage on a dedicated page.
⌨️ Command & skill palettes
Browse and run slash commands and skills from one place — including the ones discovered on your remote hosts.
🔊 Free text-to-speech
A built-in TTS tool the agent can speak through — no API key, no extra cost.
🔒 Local-first & private
Plain JSON / Markdown / SQLite in a local folder. No telemetry, no cloud database — your data stays on your machine.
Get started in two commands
Node ≥ 22 and the Claude Code CLI. That's it.
git clone https://github.com/EvanZhang008/open-walnut.git
cd open-walnut && npm install && npm start
# then open http://localhost:3456