DeepBot is an enterprise-oriented system-level AI assistant with multi-agent workflows, Feishu/WeChat/WeCom integrations, 20+ built-in tools, memory, scheduling, and security controls. It supports parallel tasks, multi-models, and dynamic system prompt assembly.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
DeepBot is a system-level AI assistant focused on enterprise productivity. It integrates with enterprise systems and supports multi-Agent collaboration to automate complex workflows, including document processing, data analysis, system monitoring, and cross-department coordination. It offers parallel task processing, scheduled tasks, skill extensions, and security controls.
How it works
DeepBot uses a modular architecture with an Electron UI, a gateway for session management, and an Agent Runtime per session. It dynamically assembles system prompts from base prompts, tool instructions, memory, and Skills, then feeds the prompt to AI models. Tools (20+ built-in) enable file operations, command execution, browser control, image generation/analysis, document analysis, AI chat, cross-session messaging, web fetching, and external integrations. Security is enforced via a path whitelist. External integrations connect to Feishu and other platforms through a Connector system for cross-platform interaction.
Getting started
Requirements (from README):
- Python: 3.11+
- Node.js: 20.0.0+ (optional, for running JS scripts)
- pnpm: 10.23.0+ (optional, for running JS scripts)
- OS: macOS, Windows (desktop), Linux/Docker
Installation
# Clone the repository
git clone https://github.com/kevinluosl/deepbot.git
cd deepbot
# Install dependencies
pnpm install
# Start in development mode
pnpm run dev
Build Desktop App
# Build for all platforms
pnpm run dist
# macOS (with code signing + notarization, requires Apple Developer account)
pnpm run dist:mac
# macOS local build (no signing, no notarization — for development/testing)
pnpm run dist:mac:local
# Windows only
pnpm run dist:win
Docker Deployment Docker deployment is available for Linux servers. If you need the Docker version, please contact the author.
To use dist:mac, see environment variable configuration in the README for Apple signing and notarization.
Recent releases
- v0.7.2 (2026-05-07): 1. 1. Skill 能力优化 4. 支持 Docker 模式 7. 支持微信、飞书、企业微信、智能客服 10. 记忆优化，节省 Token 13. 浅色主题与体验优化
Traction
2364 stars, 186 forks, 1 open issue as of the provided metrics.
Behind the repo
The project is authored by kevinluosl with links to enterprise-oriented tooling and integration capabilities (Feishu/WeChat/WeCom) via Connector system.
Caveats
- License: MIT
- Created: 2026-01-30
- Last push: 2026-05-23
- Language: TypeScript
- Node.js/OS requirements and macOS distribution considerations are described, including signed vs unsigned builds and related security prompts.