TeamClaw

# TeamClaw  Agent Subsystem Skill

https://github.com/Avalon-467/Teamclaw


## Introduction

TeamClaw is an OpenClaw-like multi-agent sub-platform with a built-in lightweight agent (similar to OpenClaw's), featuring computer use capabilities and social platform integrations (e.g., Telegram). It can run independently without blocking the main agent, or be directly controlled by an OpenClaw agent to orchestrate the built-in OASIS collaboration platform. It also supports exposing the frontend to the public internet via Cloudflare, enabling remote visual multi-agent workflow programming from mobile devices or any browser.

TeamClaw is a versatile AI Agent service providing:

- **Conversational Agent**: A LangGraph-based multi-tool AI assistant supporting streaming/non-streaming conversations
- **OASIS Forum**: A multi-expert parallel discussion/execution engine for orchestrating multiple agents
- **Scheduled Tasks**: An APScheduler-based task scheduling center
- **Bark Push**: Mobile push notifications
- **Frontend Web UI**: A complete chat interface

## Skill Scripts

All scripts are located in `selfskill/scripts/`, invoked uniformly via the `run.sh` entry point, **all non-interactive**.

```
selfskill/scripts/
 run.sh          # Main entry (start/stop/status/setup/add-user/configure)
 adduser.py      # Non-interactive user creation
 configure.py    # Non-interactive .env configuration management
```

## Quick Start

All commands are executed in the project root directory.

**Three-step launch flow: `setup` → `configure` → `start`**

### 1. First Deployment

```bash
# Install dependencies
bash selfskill/scripts/run.sh setup

# Initialize configuration file
bash selfskill/scripts/run.sh configure --init

# Configure LLM (required)
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-your-key \
  LLM_BASE_URL=https://api.deepseek.com \
  LLM_MODEL=deepseek-chat

# ⚠️ Create user account (REQUIRED — without this you CANNOT log in to the Web UI or call API)
b...

**[English](#english) | [中文](#中文)**

> **🌐 Multilingual Versions:** This project maintains an English-only branch `i18n-en` for international users. Switch via: `git checkout i18n-en`

---

<a id="english"></a>

# TeamClaw
https://github.com/Avalon-467/Teamclaw
> **OpenAI-compatible AI Agent with a built-in programmable multi-expert orchestration engine and one-click public deployment.**
>
> **Skill Mode:** This repository is designed to run and be documented in a Skill-oriented workflow (see `SKILL.md`).

TeamClaw exposes a standard `/v1/chat/completions` endpoint that any OpenAI-compatible client can call directly. Internally it integrates the **OASIS orchestration engine** — using YAML schedule definitions to flexibly compose expert roles, speaking orders, and collaboration patterns, breaking complex problems into multi-perspective debates, voting consensus, and automated summaries.

## Highlights

### 1. OpenAI-Compatible API

```bash
curl http://127.0.0.1:51200/v1/chat/completions \
  -H "Authorization: Bearer <user>:<password>" \
  -H "Content-Type: application/json" \
  -d '{"model":"mini-timebot","messages":[{"role":"user","content":"Hello"}],"stream":true}'
```

- Fully compatible with OpenAI Chat Completions format, streaming & non-streaming
- Multi-turn conversation, image input (Vision), audio input, file upload, TTS
- Works with ChatBox, Open WebUI, Cursor, or any OpenAI-compatible client
- Multi-user + multi-session isolation, SQLite-persisted conversation memory

### 2. OASIS Orchestration — A Programmable Expert Collaboration Engine

**This is the core design of the entire project.**

Traditional multi-agent systems are either fully parallel or fixed pipelines, unable to adapt to different scenarios. The OASIS engine uses a concise **YAML schedule definition** that lets users (or the AI Agent itself) precisely orchestrate every step of expert collaboration:

```yaml
# Example: Creative and Critical experts clash first, then everyone summarizes
v...