astrbot_plugin_jev_active_reply
AstrBot plugin where Jev decides whether the bot should join a group conversation; the main model still writes the reply.
Overview
Jev Active Reply is an AstrBot plugin that lets a bot join group chats in character: following the topic, picking up interesting content and staying quiet when people are fine without it. Jev quickly judges whether a message is worth replying to; the actual reply is still generated by the main model configured in AstrBot, with its persona, context, memory and images unchanged.
It works on whitelisted or blacklisted groups, can take over @-mentions and private chats, merges consecutive messages from the same person, and supports multiple keys with rotation. Jev access can be official TypeSafe, a custom relay speaking the native systemone protocol, or a third-party relay run by the plugin author, which the README openly labels as self-operated with its own pricing. It requires AstrBot 4.26.8+ below 5.0; docs are in Chinese.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this group message worth the bot replying to?(inferred) | yes · no |
How it works
- Group message arrives in a working group
- Merge consecutive messages from the same person
- Jev judges whether to reply
- If yes, AstrBot's main model generates the reply
Strengths
- Only judgment goes to Jev; persona and memory stay in AstrBot
- Multiple keys with rotation
- Explicit mentions bypass the judgment
Caveats
- Recommended relay is run by the plugin author
- Chinese docs; AstrBot version constraints
- No licence stated
Getting started
Install from the AstrBot plugin market, set the group scope, choose a Jev service and enter its API key.At a glance
- Type
- Project
- Status
- production
- Language
- Python
- Runtime
- AstrBot plugin
- Has code
- yes
Use cases and integrations
How curated lists describe it
Jev主动回复插件 · 作者木有知 · TypeSafe/MindsHub多Key与同人连续补充合并.
hellogumbo/awesome-jev
Frequently asked questions
Does Jev write replies?
No, it only decides whether to reply; the main model writes the reply.
Do I have to use the author's relay?
No, official TypeSafe keys and custom systemone relays are supported.
Which AstrBot versions?
4.26.8 and later, below 5.0.
Related projects
- jev-chat-windows★ 802
Windows WeChat reply assistant: local offline OCR reads the chat, Jev judges intent and tension and ranks three drafted replies to fill in.
ProjectproductionPython iOS custom keyboard that shows a copied message's intent, risk level and candidate replies inside any chat app, filling but never sending.
AppbetaSwiftWindows desktop chat assistant that OCRs a selected chat region, has Jev analyse the conversation, and ranks drafted replies for copying.
ProjectbetaPython, TypeScriptmacOS chat overlay that reads the current chat window and shows the incoming message's intent, risk and candidate replies, read-only.
ProjectbetaPythonUnofficial fork of jev-chat-windows: WeChat overlay with local OCR and drafted replies, adding optional auto-send and a knowledge base.
HookbetaPythonWeChat reply assistant fork: DeepSeek drafts three replies, Jev pre-judges, reviews and ranks them; auto-send is cancellable.
ProjectbetaPython