User repository on GitHub
AstrBot 群聊增强插件（Chat_PLUS fork）：集成阿里云 System One Jev 决策模型，插话/主动开场智能复核，每群限频与降级保护
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Integrations & Adapters
Astrbot Plugin Jev — czyczy23
A fork of astrbot_plugin_group_chat_plus that adds Alibaba Cloud's System One Jev decision model after the original random probability gate, reviewing whether the bot should interject, with per-group rate limiting and degradation protection.
- Stars
- 3
- Language
- Python
- License
- AGPL-3.0
- Reading time
- 2 min
- Published by
- Community
- Author
- czyczy23
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Astrbot Plugin Jev — ba7lcy.
Works forJev for Decision gating
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceRequires API key
Highlights
- Fork of Him666233/astrbot_plugin_group_chat_plus (v1.2.3.hotfix.2) adding a 50-70 ms System One review after the random gate.
- Flow: group message, original probability gate, should-we-interject review, read-the-room AI, reply.
- When P(yes) reaches the threshold it passes and suggests an interjection style: question, share or agreement.
- Below threshold the bot stays quiet without consuming quota; timeout or error degrades to the original logic instead of going silent.
- AGPL-3.0, AstrBot v4.11.0 or newer, version V1.3.0.jev.1; the README ships a decision-flow simulator page.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt truncates inside the capability table, so the full intervention-mode list, configuration keys and the Alibaba Cloud model and pricing details are not evidenced.
Questions about this entry
Short answers drawn from the linked project or page.
A group-chat enhancement plugin for AstrBot, forked from astrbot_plugin_group_chat_plus, that integrates the Alibaba Cloud System One Jev decision model to review whether the bot should interject or proactively open a conversation.
Upstream gates speaking on a pure random probability and does not know what the group is discussing. This fork keeps that gate and appends a 50 to 70 ms decision-model review after it, deciding whether the interjection is worth making.
A group message passes the original probability gate, then the System One review asks whether interjecting is worthwhile, then the read-the-room AI writes the reply. When P(yes) is at or above the threshold, the system also suggests an interjection style.
The README says a timeout or error becomes an undecided state that degrades back to the original plugin logic, so the bot never goes fully silent because of a decision-model failure.
The README advertises three modes, with off as the default, where behavior is described as byte-for-byte identical to the original plugin. The digest excerpt truncates inside the mode table, so the other two are not named here.
AstrBot v4.11.0 or newer and access to the Alibaba Cloud System One decision model. The repo is AGPL-3.0, carrying over the upstream license, and the README links a decision-flow simulator for previewing the logic.
The excerpt truncates inside the capability table, so the full mode list, the exact configuration keys, per-group rate limits and the Alibaba Cloud model and pricing are not evidenced.
More Jev resources like this
An AstrBot plugin that asks a decision model whether the bot should speak at all: it screens wake-word and ordinary group messages before interjecting, then re-checks each drafted reply before it is sent, without changing a word of the text.
Jev Integrations & Adapters#community#github#python
Community
ba7lcy/astrbot-plugin-jevPython
ba7lcy/astrbot-plugin-jevPythonDrop-in guardrails for any AI app, powered by Jev: it asks narrow yes/no questions about text, such as whether something is a prompt injection, gets a probability, and lets the app allow, review or block in milliseconds, with adapters for Gemini, Anthropic, OpenAI and FastAPI.
Jev Integrations & Adapters#community#github#python
A GitHub App that routes pull-request review work through Jev: it ingests the webhook, normalizes the PR context, gets a LOW, NORMAL or SPECIALIST decision, and a deterministic policy layer maps it to auto-approval, a review request or a check-run update.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
hexyedev/jevprPython
hexyedev/jevprPythonA Python toolkit that hands browser sub-tasks to Jev instead of the coding agent: one fast_run call lets Jev drive clicks and typing step by step, and the agent gets back a typed outcome or a typed reason to stop.
Jev Integrations & Adapters#community#python#browser
Community
danielnc/jev-browsePython
danielnc/jev-browsePythonAn MCP gateway that routes tool selection through Jev: for each request, Jev answers one yes/no question per server and per tool, and the LLM only sees the tools that passed. The repo's benchmark covers 649 tools at 1/32 of a comparable routing cost.
Jev Integrations & Adapters#community#github#mcp
Community
ini8labs/jev-mcp-routerPython
ini8labs/jev-mcp-routerPythonA pi coding-agent extension that ranks long-term memory files against the current context with a yes/no classifier read from native token logits. It triggers on cold start, post-compaction and an on-demand tool, and offers a prior, not a verdict.
Jev Integrations & Adapters#community#github#python
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.