Stream Feishu chat events and send replies, files, and reactions via CLI subcommands.
npx skills add https://github.com/bencode/rooma --skill rooma
Please help me install this Agent Skill. Skill: rooma Source: https://github.com/bencode/rooma/tree/main/.claude/skills/rooma Command: npx skills add https://github.com/bencode/rooma --skill rooma
rooma removes the “one-shot reply” limitation of typical chat integrations by letting an AI agent stay present in Feishu chats, listen to ambient context in real time, and take action when mentioned or when a clear task appears.
Example use case: when a project question appears in a group where the bot is @-mentioned, rooma pulls recent context, consults the room’s stated purpose/announcement, then responds briefly while marking completion with a reaction if appropriate.
Tell the skill to start a Feishu collaboration session by saying “start feishu”, then wait for the monitor stream to come online and respond to the next @-mention event.
High-intent search queries and answers about installing and using this skill.
You can keep an AI agent live in a Feishu chat by launching a WebSocket monitor that streams inbound messages as actionable JSON events, enabling the agent to listen to ambient context and respond when mentioned.
Yes, a Feishu chat bot can pull room context and member lists by using CLI subcommands to fetch chat information, members, and pinned announcements before orchestrating an automated reply or reaction.
WebSocket event streaming for agent collaboration works by tailing JSON stdout events from a WS monitor in real time, allowing the AI agent to process p2p messages, group @-mentions, and ambient chatter.
The best way to automate message escalation to humans in a Feishu group is by using the provided CLI subcommands to send targeted help requests when the agent decides a task requires human intervention.
Yes, this real-time Feishu bot approach supports sending files and reactions through specific CLI subcommands, allowing the agent to acknowledge task completion or share documents directly in the chat.
You should not use a live WS monitor for message automation if your use case only requires a single one-shot reply, as this approach is designed for persistent session-aware collaboration and context building.
9AshwinMonitor Feishu events via WebSocket and output NDJSON with regex routing.
LIMITLESS-LONGEVITYPersist WhatsApp emoji reactions in SQLite and send them via MCP tools.
nadicodeaiQuery group info, find members, and send DMs within group chats.
SpaceZephyrCapture real-time Lark platform events via WebSocket long connection with NDJSON output.
