惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

TaoSecurity Blog
TaoSecurity Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
F
Fortinet All Blogs
Cisco Talos Blog
Cisco Talos Blog
D
Darknet – Hacking Tools, Hacker News & Cyber Security
S
Secure Thoughts
美团技术团队
雷峰网
雷峰网
Hugging Face - Blog
Hugging Face - Blog
博客园_首页
C
CXSECURITY Database RSS Feed - CXSecurity.com
Engineering at Meta
Engineering at Meta
人人都是产品经理
人人都是产品经理
月光博客
月光博客
T
Tor Project blog
P
Privacy & Cybersecurity Law Blog
Recorded Future
Recorded Future
I
Intezer
博客园 - 【当耐特】
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
GbyAI
GbyAI
罗磊的独立博客
V
V2EX
Google DeepMind News
Google DeepMind News
D
DataBreaches.Net
Last Week in AI
Last Week in AI
T
Tailwind CSS Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
A
About on SuperTechFans
Scott Helme
Scott Helme
Vercel News
Vercel News
Spread Privacy
Spread Privacy
T
Threat Research - Cisco Blogs
Recent Announcements
Recent Announcements
Hacker News: Ask HN
Hacker News: Ask HN
C
CERT Recently Published Vulnerability Notes
G
Google Developers Blog
B
Blog
博客园 - 叶小钗
WordPress大学
WordPress大学
博客园 - 聂微东
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Jina AI
Jina AI
IT之家
IT之家
C
Cybersecurity and Infrastructure Security Agency CISA
P
Palo Alto Networks Blog
小众软件
小众软件
博客园 - Franky
Microsoft Azure Blog
Microsoft Azure Blog
AWS News Blog
AWS News Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店 GitHub - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
GitHub - erickalfaro/multitable
ericksnetwor · 2026-04-25 · via Hacker News: Show HN

MultiTable logo

One cockpit for every AI coding agent, dev server, and terminal in your workflow.
Because tmux wasn't built for the day Claude, Codex, Aider, and npm run dev all need your attention at once.

License: MIT Platforms: macOS, Linux, Windows Node >=18 100% local Status: MVP CI

MultiTable in action


What is this?

MultiTable is a local, browser-based dashboard for the chaos of agentic coding. A small Node.js daemon on your machine spawns your processes via real PTYs (thanks, node-pty), persists state in SQLite, and serves a React UI at http://localhost:3000. One tab. Every project. Every agent. Every dev server.

It's agent-agnostic — Claude Code, Codex, Aider, Cursor's CLI, your own scripts. Anything you'd run in a terminal runs in MultiTable. Claude Code gets first-class hooks integration (in-UI permission prompts, cost tracking, "done" notifications), but nothing about the rest of the app cares which model is on the other end of the PTY.

Privacy: the daemon runs entirely on your machine. No accounts, no telemetry, no outbound calls. The only network traffic is between your browser and localhost (or your tailnet, if you turn that on).

Before MultiTable                      After MultiTable
┌──────┐ ┌──────┐ ┌──────┐             ┌──────────────────────────────┐
│Claude│ │ Codex│ │ npm  │             │  MultiTable (one tab)        │
│ Code │ │      │ │ dev  │             │                              │
└──────┘ └──────┘ └──────┘             │  All processes. One view.    │
┌──────┐ ┌──────┐ ┌──────┐             │  Status at a glance.         │
│Queue │ │ Logs │ │ bash │             │  Auto-restart on crash.      │
│worker│ │      │ │      │             │  Approve perms in the UI.    │
└──────┘ └──────┘ └──────┘             └──────────────────────────────┘
 6+ scattered terminals                  1 tab, everything managed

Why you might want it

  • You run more than one coding agent at a time (Claude Code + Codex + Aider...) and lose track of which terminal is which.
  • Your Claude Code session throws a permission prompt while you're on another tab and the run stalls for 30 minutes.
  • Your dev server crashes, silently, inside one of twelve tmux panes.
  • You want to check on a running agent from your iPad in the kitchen over Tailscale.
  • You want cost and token usage per session without scraping logs.

Why I built this

I wanted to vibe-code from my phone.

Not "SSH into a box and squint at vim" — Termux has done that for years and it's miserable. I wanted the real thing: a proper file explorer, real terminals, status at a glance for every running agent and dev server, and the ability to approve a Claude Code permission prompt from the couch without losing context. I wanted to kick off half a dozen experiments across different repos in the morning and check on each one between meetings.

Nothing existed that did all that, so I built MultiTable.

Code from anywhere

The daemon runs on your dev machine. The UI runs in any browser. Stretch one over Tailscale and your dev environment goes wherever you do — phone on the train, iPad on the couch, borrowed laptop at a coffee shop. Same projects, same agents, same scrollback, same git diffs. You can kick off a Claude Code session from your desktop, leave the house, approve its permission prompts from your phone, and read the diff it produced on your iPad while you make dinner.

Nothing leaves your machine. Tailscale handles the encrypted tunnel; MultiTable just listens on a port. No cloud sync, no relay server, no account.

# ~/.config/multitable/config.yml
host: 0.0.0.0   # bind to your tailnet, not the public internet

Then open http://<your-tailscale-hostname>:3000 from any device on the tailnet. That's it.

Features

  • One sidebar, every process. Sessions (AI agents), commands (dev servers, workers), and terminals (ad‑hoc shells) in a single tree, grouped by project.
  • Permission prompts surface in the UI. No more missed Claude Code "Allow / Deny / Always Allow" prompts buried in a pane — accept from any device on your tailnet.
  • Browser notifications + sound chimes when an agent finishes, needs attention, or asks a permission question. Walk away, hear when it's your turn.
  • Auto-restart with backoff. Configurable autorestartMax, autorestartDelayMs, and windowed reset — crashes don't mean silence.
  • File-watch restart for dev servers — edit src/**/*.ts, the watcher restarts the right process.
  • Cost & token tracking per Claude Code session, parsed from hook events.
  • Git diffs per session, via simple-git, so you can see what an agent actually changed.
  • Session resume. A Claude Code session remembers its claudeSessionId, and on daemon startup you decide whether to resume or start fresh.
  • Command palette (cmdk) for fuzzy-jumping between projects, processes, and actions.
  • SQLite persistence. Projects, sessions, commands, scrollback — all survive restarts.
  • LAN / Tailscale / mobile. Bind the daemon to 0.0.0.0, open the UI from your phone or iPad — same dashboard, with a touch toolbar.
  • Themeable. Built-in light/dark themes plus user-defined themes via CSS variables.
  • Config-as-code. Drop an mt.yml in a project and everything autostarts the way you described.

How it compares

tmux / zellij Warp / Wave MultiTable
Multiple PTYs
Survives reboot ⚠️ session files ✅ SQLite
Per-process auto-restart
File-watch restart
Agent permission prompts in UI ✅ (Claude Code)
Cost / token tracking ✅ (Claude Code)
Git diff per session
Use from your phone
100% local, no account

"Isn't this just OpenClaw?"

No — different tool, different problem. The two are genuinely complementary.

OpenClaw is a personal AI agent you talk to through messaging apps (WhatsApp, Telegram, Slack…) that runs skills on your behalf. One of its many skills can delegate work to Claude Code or Codex.

MultiTable is the cockpit for those coding agents. You're watching the actual PTY, scrubbing the scrollback, approving the permission prompts in-line, reading the git diff per session. OpenClaw dispatches work to an agent; MultiTable lets you sit in front of the agent and steer it.

Use OpenClaw when you want to message an assistant from your phone and have it go do things. Use MultiTable when you want to be the operator — see every running session, every prompt, every line of output — just from a browser instead of a wall of terminals. There's no reason you can't run both.

A few deliberate scope choices that follow from this framing:

  • Localhost-only by default (127.0.0.1). LAN / Tailscale access is one config line away, but the default is not a public bind.
  • No plugin or skill registry. MultiTable runs the processes you explicitly spawn. There's no marketplace of community code that auto-loads into your daemon.
  • Coding-loop only. No messaging bridges, no smart-home control, no general-purpose skill catalog. Every screen is built around dev-loop primitives: sessions, dev servers, terminals, diffs.

Screenshots

📸 Drop screenshots into docs/images/ and these will render.

Dashboard Session detail
Dashboard Session detail
Terminal view Permission request
Terminal view Permission modal
ASCII preview (for repo readers without images)
┌──────────────┬───────────────────────────────────────────────┐
│  SIDEBAR     │  MAIN PANE                                    │
│              │                                               │
│  my-project  │  $ claude                                     │
│   SESSIONS   │  > I'll help you refactor the API...          │
│   ● Claude   │  Reading src/api/routes.ts...                 │
│   ● Codex    │  █                                            │
│   TERMINALS  │                                               │
│   ● Term 1   │  ┌─ Permission Request ─────────────────┐     │
│   COMMANDS   │  │ Claude Code wants to use: Edit       │     │
│   ● npm:dev  │  │ File: src/api/routes.ts              │     │
│   ● Queue    │  │ [Allow]  [Deny]  [Always Allow]      │     │
│              │  └──────────────────────────────────────┘     │
├──────────────┴───────────────────────────────────────────────┤
│ [Focus][Pause][Clear][Stop][Restart]   CPU 2.1%  MEM 43MB   │
└──────────────────────────────────────────────────────────────┘

Installation

MultiTable is pre-npm-publish — you install it from source. All three platforms follow the same three-step dance:

  1. Install prerequisites (Node + build tools for native modules).
  2. Clone + install + build.
  3. Link the mt CLI so you can run mt start from anywhere.

Prerequisites (all platforms)

Why native build tools? MultiTable depends on better-sqlite3 and node-pty, which are native C/C++ modules. npm install will attempt to download prebuilt binaries; if none exist for your platform/Node version, it falls back to building from source and will need a compiler.

🍎 macOS

# 1. Install Xcode Command Line Tools (for native module builds)
xcode-select --install

# 2. Clone, install, build
git clone https://github.com/erickalfaro/multitable.git
cd multitable
npm install
npm run build

# 3. Make `mt` available globally
cd packages/cli && npm link && cd ../..

🐧 Linux (Debian / Ubuntu)

# 1. Install build tools
sudo apt-get update
sudo apt-get install -y build-essential python3 git

# 2. Clone, install, build
git clone https://github.com/erickalfaro/multitable.git
cd multitable
npm install
npm run build

# 3. Make `mt` available globally
cd packages/cli && sudo npm link && cd ../..

On Fedora / RHEL: replace step 1 with sudo dnf install -y gcc-c++ make python3 git. On Arch: sudo pacman -S --needed base-devel python git.

🪟 Windows 10 / 11

Use PowerShell, not cmd.exe. A few of the npm scripts rely on Unix-ish shell idioms (cp), which PowerShell aliases but cmd.exe does not.

# 1. When installing Node from nodejs.org, check the box:
#    "Automatically install the necessary tools for native modules"
#    (That pulls Visual Studio Build Tools + Python 3 via Chocolatey.)

# 2. Clone, install, build
git clone https://github.com/erickalfaro/multitable.git
cd multitable
npm install
npm run build

# 3. Make `mt` available globally
cd packages\cli
npm link
cd ..\..

Known Windows limitation: per-process CPU % shows as 0 on Windows (the metrics poller uses Unix ps as a fallback). Memory and state work normally. PR welcome.

Uninstall

cd multitable/packages/cli && npm unlink -g
cd ../.. && rm -rf node_modules
rm -rf ~/.config/multitable       # config
rm -rf ~/.local/share/multitable  # SQLite db, scrollback (Linux/macOS path)

Quick start

mt start          # start the daemon on http://localhost:3000
mt open           # open the UI in your browser

…or skip the CLI and run dev mode (daemon + Vite with HMR):

npm run dev
# Daemon:      http://127.0.0.1:3000
# Vite dev UI: http://127.0.0.1:5173  (proxies /api and /ws to the daemon)

From the empty dashboard:

  1. Click + Add Project → point it at any directory on disk.
  2. Add a session (claude, codex, aider, whatever your agent is) or a command (npm run dev).
  3. Hit Start.
  4. Grab a drink.

Configure a project with mt.yml

Drop this at the root of any project and MultiTable will pick it up on startup:

name: my-project
sessions:
  - name: Claude Code
    command: claude
    autostart: true
commands:
  - name: npm:dev
    command: npm run dev
    autostart: true
    fileWatchPatterns:
      - "src/**/*.ts"
  - name: Queue
    command: php artisan queue:work
    autostart: true
    autorestart: true
    autorestartMax: 5
    autorestartDelayMs: 2000

Global daemon config

~/.config/multitable/config.yml (Linux/macOS) — or the equivalent on Windows via env-paths:

port: 3000
host: 127.0.0.1   # change to 0.0.0.0 to accept LAN / Tailscale connections

Remote access setup

See Code from anywhere above for the why. The full recipe:

  1. Install Tailscale on your dev machine and on every device you want to reach it from. Sign in to the same tailnet on each.
  2. Set host: 0.0.0.0 in ~/.config/multitable/config.yml and restart the daemon.
  3. Find your dev machine's tailnet name (tailscale status shows it) and open http://<tailscale-hostname>:3000 from any device on the tailnet.

A few things worth noting:

  • Don't bind to 0.0.0.0 without Tailscale unless you know what you're doing. The daemon has no auth — anything on your network can reach it.
  • Mobile UI is responsive — there's a touch toolbar and a swipe-out sidebar built specifically for phone-sized screens.
  • WebSocket reconnects automatically when you switch networks (Wi-Fi → cellular and back), so you can walk out the door mid-session.

Architecture

flowchart TB
    subgraph Browser["Browser (laptop, iPad, phone)"]
        UI["React + xterm.js UI"]
    end

    subgraph Daemon["mt daemon (Node.js on localhost)"]
        Express["Express<br/>REST API"]
        WS["ws<br/>WebSocket stream"]
        PTY["node-pty<br/>ManagedProcess map"]
        DB[("SQLite<br/>better-sqlite3")]
        Watcher["chokidar<br/>file watcher"]
        Git["simple-git<br/>diffs"]
        Hooks["Claude Code<br/>hook receiver"]
    end

    UI -- "REST: CRUD" --> Express
    UI <-- "WS: pty I/O, state, metrics, permissions" --> WS

    Express --> DB
    Express --> PTY
    WS <--> PTY
    Watcher --> PTY
    PTY --> DB
    Hooks --> DB
    Hooks --> WS

    ClaudeCode["Claude Code<br/>(spawned session)"] -- "HTTP hooks" --> Hooks
    PTY -- "spawns" --> ClaudeCode
Loading

See docs/SPEC.md for the full product specification and docs/OVERVIEW.md for a deeper visual walkthrough.

Repository layout

packages/
  daemon/   Node.js backend — Express + ws + node-pty + SQLite
  web/      React frontend — xterm.js + Zustand + Tailwind
  cli/      `mt` command (commander)
docs/       Product spec and overview diagrams

Roadmap

  • v0.1 Foundation — daemon + React + single terminal + projects
  • v0.2 Persistence — SQLite + dashboard + status indicators
  • v0.3 Git tools — diff viewer per session
  • v0.4 Claude Code integration — hooks, in-UI permissions, options, resume, cost & token tracking
  • v0.5 Global keyboard shortcuts (Ctrl+K palette, process jumps) and richer search
  • v0.6 Polish — conflict detection improvements, CLI ergonomics, more themes, packaged binaries

Contributing

Contributions of all sizes welcome — bug reports, docs fixes, entire features. See CONTRIBUTING.md.

Good first issues are labelled good first issue. The most useful early PRs would be:

  • Global keyboard shortcuts (the command palette opens, but nothing has bound Ctrl+K yet).
  • Windows per-process CPU % (the metrics poller currently relies on Unix ps).
  • Adapters for additional agents beyond Claude Code (Codex, Aider, etc. work as raw PTYs today; deeper hook-style integration is wide open).

Security

Please don't open public issues for vulnerabilities. See SECURITY.md.

License

MIT — see LICENSE.


Built with node-pty, React, SQLite, and a healthy refusal to tmux one more thing.