# kevinluosl/deepbot

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

Repository: https://github.com/kevinluosl/deepbot
Canonical: https://ross.abutalabs.com/products/deepbot
Homepage: https://glint-mvt.com/deepbot/
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent-skills, agentic-workflow, ai-agents, openclaw, agent-tools, agentos, harness, harness-engineering
Last push: 2026-05-23T05:49:13+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 51, longevity 15
- inputs: {"age_days": 215, "days_push": 102, "days_rel": 118, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2272, forks 178 (observed 2026-08-28T04:06:33.210397+00:00)

## What it is
DeepBot is a system-level AI assistant desktop application (Electron/TypeScript) that automates enterprise and personal workflows through multi-agent collaboration, with 20+ built-in tools, scheduled tasks, memory, and skill extensions. It runs locally with strict security controls and integrates with Feishu, WeChat, and WeCom, supporting both local and cloud LLMs.

## Use cases
- automate enterprise workflows with AI agents
- send personalized emails and greeting cards to employees automatically
- control my computer and browser to complete tasks like a human assistant
- schedule recurring AI tasks with cron
- run a shared AI assistant on an edge box with Docker
- integrate an AI assistant with Feishu
- do market research and web data gathering automatically

## When to choose
- you want a local-first desktop AI agent that can execute commands, manage files, and control the browser
- your team uses Feishu/WeChat/WeCom and needs AI integrated into messaging and documents
- you need parallel task execution, cron scheduling, and extensible skills in one assistant
- you want to deploy a shared team AI hub on low-resource edge hardware via Docker

## When to avoid
- you only need a simple chatbot without system access or tool execution
- you require a cloud-hosted managed service rather than a self-run desktop app
- you need a lightweight CLI-only agent without a GUI
- your platform is not macOS, Windows, or Linux/Docker

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chatbot, workflow-automation, scheduling, web-scraping, image-processing, developer-tools
- domain: developer-tools, large-language-models
- platform: windows
- tags: feishu-integration, multi-agent, local-first, skills, memory-system, enterprise-assistant, browser-automation, ai-agents, automation, macos, linux, docker, desktop, electron, typescript, nodejs

## Member repositories
- kevinluosl/deepbot (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.210397+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:41:42.890224+00:00, confidence not recorded.
  - readme: https://github.com/kevinluosl/deepbot (fetched 2026-08-28T04:06:33.210397+00:00, sha d3da9d3e09d0)
  - homepage: https://glint-mvt.com/deepbot/ (fetched 2026-08-29T10:22:27.757038+00:00, sha 3e1ce24462cd)
- Data as of 2026-08-30T08:39:29.467469+00:00.