Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A lightweight web dashboard for viewing all your OpenClaw Bots/Agents/Models/Sessions status at a glance.
| Date | Stars |
|---|---|
| 2026-07-31 | 2012 |
| 2026-08-02 | 2011 |
| 2026-08-06 | 2011 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
# OpenClaw Dashboard（English）
A lightweight web dashboard for viewing all your [OpenClaw](https://github.com/openclaw/openclaw) Bots/Agents/Models/Sessions status at a glance.
<br>Bots Dashboard：
Pixel Office：
## Background
When running multiple OpenClaw agents across different platforms (Feishu, Discord, etc.), managing and monitoring them becomes increasingly complex — which bot uses which model? Are the platforms connected? Is the gateway healthy? How are tokens being consumed?
This dashboard reads your local OpenClaw configuration and session data, providing a unified web UI to monitor and test all your agents, models, platforms, and sessions in real time. No database required — everything is derived directly from `~/.openclaw/openclaw.json` and local session files. Plus, a fun pixel-art office brings your agents to life as animated characters walking around, sitting at desks, and interacting with furniture.
## Features
- **Bot Overview** — Card wall showing all agents with name, emoji, model, platform bindings, session stats, and gateway health status
- **Model List** — View all configured providers and models with context window, max output, reasoning support, and per-model test
- **Session Management** — Browse all sessions per agent with type detection (DM, group, cron), token usage, and connectivity test
- **Statistics** — Token consumption and average response time trends with daily/weekly/monthly views and SVG charts
- **Skill Management** — View all installed skills (built-in, extension, custom) with search and filter
- **Alert Center** — Configure alert rules (model unavailable, bot no response) with Feishu notification delivery
- **Gateway Health** — Real-time gateway status indicator with 10s auto-polling and one-click jump to OpenClaw web UI
- **Platform Test** — One-click connectivity test for all Feishu/Discord bindings and DM sessions
- **Auto Refresh** — Configurable refresh interval (manual, 10s, 30s, 1min, 5min, 10min)
- **i18n** — Chinese and English UI language switching
- **Dark/Light Theme** — Theme switcher in sidebar
- **Pixel Office** — Animated pixel-art office where agents appear as characters that walk, sit, and interact with furniture in real time（The feature is inspired by Pixel Agents）
- **Live Config** — Reads directly from `~/.openclaw/openclaw.json` and local session files, no database needed
## Preview
## Getting Started
See [Quick Start Guide](quick_start.md) for prompt/git/skill startup options.
```bash
# Clone the repo
git clone https://github.com/xmanrui/OpenClaw-bot-review.git
cd OpenClaw-bot-review
# Install dependencies
npm install
# Build
npm run build
# Start dev server
npm run start
```
Open [http://localhost:3000](http://localhost:3000) in your browser.
## Tech Stack
- Next.js + TypeScript
- Tailwind CSS
- No database — reads config file directly
## Requirements
- Node.js 18+
- OpenClaw installed with config at `~/.openclaw/openclaw.json`
## Configuration
By default, the dashboard reads config from `~/.openclaw/openclaw.json`. To use a custom path, set the `OPENCLAW_HOME` environment variable:
```bash
OPENCLAW_HOME=/opt/openclaw
npm run build
npm run start
```
### R&D Council operator APIs
The Self-Improvement and R&D Council actions can write local files such as `rd-council-items.json`, `idea_ledger.json`, decision logs, and local work-order handoff state. For safety, those operator APIs require an explicit token by default:
```bash
OPENCLAW_OPERATOR_TOKEN="replace-with-a-long-random-token" npm run start
```
Then set the same token in the browser console for the local dashboard origin:
```js
localStorage.setItem("openclaw_operator_token", "replace-with-a-long-random-token")
```
For trusted local developmeExcerpt of 8,262 characters
Read on GitHub
282
19
7
3
2
Jude Wang · Zhejiang University · China
2
2
2
2
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5e3bb44f0cb3dddf, llm:Repository description: "A lightweight web dashboard for viewing all your OpenClaw Bots/Agents/Models/Sessions status at a glance." Topics: open-claw, openclaw. Language: TypeScript (web dashboard).
matched fp:5e3bb44f0cb3dddf, llm:Repository description: "A lightweight web dashboard for viewing all your OpenClaw Bots/Agents/Models/Sessions status at a glance." Topics: open-claw, openclaw. Language: TypeScript (web dashboard).