User repository on GitHub
astrbot-plugin-jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Astrbot Plugin Jev — ba7lcy
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.
- Stars
- 3
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- BA7LCY
- Last verified
- Oct 2026
Works forJev for Decision gating
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceRequires API key
Highlights
- AstrBot plugin, version v2.0.0, that gates bot speech in three scenes: wake-word messages, unaddressed interjections and pre-send review.
- The decision model only sends or skips; the reply text still comes from the language model and persona configured in AstrBot.
- Questions and release conditions are editable JSON in the console's configuration settings; the default balanced profile works out of the box.
- Requires AstrBot 4.27.4 or newer, below 5.0, and a decision-model API key; dependencies reuse AstrBot's existing aiohttp.
- Install by placing the repo at AstrBot/data/plugins/astrbot-plugin-jev, reloading the plugin list, then setting api_key.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt truncates mid-sentence in the setup steps, so the full settings table, group-takeover behavior and any rate or cost limits are not evidenced. No license is listed in the GitHub metadata.
Questions about this entry
Short answers drawn from the linked project or page.
An AstrBot plugin that puts a decision model in front of the bot's speech: it decides whether to pick up a message and whether a drafted reply should be sent, while the reply text itself still comes from the model and persona you configure in AstrBot.
In three scenes: named messages, ordinary unaddressed messages and a send-time review. Each gets a should-we-speak question before the bot opens its mouth, and every drafted reply is re-checked before sending. The plugin never rewrites the reply; it only decides send or skip.
AstrBot 4.27.4 or newer, below version 5.0, plus an API key for a decision-model endpoint. Python dependencies are limited to aiohttp, which AstrBot already ships, so there is no frontend build and no separate database to deploy.
Place the repository at AstrBot/data/plugins/astrbot-plugin-jev by git clone or zip download, reload the plugin list in AstrBot's plugin manager, then fill in api_key in the plugin settings. To change endpoints, edit api_base and model together.
Yes. The questions and release conditions for each scene are JSON under the console's configuration settings. The default configuration is the balanced profile, described as usable as soon as the plugin is installed and switched on.
No. Reply content is still generated by the language model and persona configured in AstrBot; the plugin only decides whether a message is picked up and whether a reply is sent, and its master switch is separate from group takeover.
The 2026-10-17 README excerpt is truncated mid-setup, so the full settings table, group-takeover behavior and any cost or rate limits are not evidenced. The GitHub metadata also lists no license for the repository.
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
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.
Jev Integrations & Adapters#community#github#python
Community
czyczy23/astrbot_plugin_jevPython
czyczy23/astrbot_plugin_jevPythonMore Jev resources like this
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.
Jev Integrations & Adapters#community#github#python
Communityczyczy23/astrbot_plugin_jevPython
czyczy23/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.