CountBot
Lightweight open-source AI Agent optimized for Chinese users | Native support for domestic large-model coding plans | Compatible with the OpenClaw Skills ecosys
What is CountBot?
Lightweight open-source AI Agent optimized for Chinese users | Native support for domestic large-model coding plans | Compatible with the OpenClaw Skills ecosystem | Integrated with WeChat ClawBot, Weibo Lobster, Feishu, DingTalk, QQ, Xiaozhi AI, Telegram and dsh.
Overview of CountBot
What it is
CountBot is a lightweight, low-footprint AI assistant that runs on your server and stays up. It binds to chat tools you already use, such as Lark, WeCom, WeChat, QQ, DingTalk, Telegram, Weibo, and ServerChan, allowing you to call it directly from those platforms or through a web interface. Unlike a plain chat bot, CountBot can execute work: it reads and writes files, runs commands, searches the web, takes screenshots, and sends media. Recurring routines can be wrapped into skills and run on a schedule, with results delivered to a chosen channel.
Key features
- Skill system: turn recurring routines into skills that load automatically as callable capability; supports enable/disable, parameter configuration, and SkillsHub installs, with a built-in
skill-creatorfor guided creation - Multi-agent teams: three orchestration modes (pipeline,graph,council) for complex work; teams can carry their own model configuration - Session-level model configuration: switch models inside a session without affecting the global default; adjust reasoning effort per session - Long-term memory: keeps context across sessions so earlier instructions do not have to be repeated - 22 built-in model providers covering mainstream Chinese and international models, plus OpenAI-compatible custom endpoints and local inference - Channel matrix: a single workspace serves multiple channels, bot accounts, and business entry points
Use cases
- Daily digest delivery: scheduled tasks fetch and summarize topics by cron, then push to Lark, WeChat, QQ, ServerChan and other channels - In-group assistant: mention the bot in a group to ask questions, look up material, draft content, and call tools - Scheduled tasks and reminders: run arbitrary instructions on a schedule with selectable delivery target, bot account, and model per task - Proactive greetings: a heartbeat mechanism starts conversations or reminders at a set frequency, suited for shift handover briefings - Material handling: web scraping, document parsing, knowledge base retrieval, file read/write, and batch processing - Multi-role collaboration: split complex work across an Agent Team, run it in parts, and consolidate - External coding tools: connect Claude Code, Codex, OpenCode, and dsh (DeepSeek Harness) as callable tools or agents bound to a channel
Getting started
See the repository README for installation instructions.
License and pricing
MIT license. Open source.
Based on the project's public README and repository metadata.