User repository on GitHub
Shugo is a context-aware Discord auto-moderation bot powered by Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Shugo
A self-hostable Discord auto-moderation bot written in Go and powered by Jev, TypeSafe's System One model: it reads every message, asks Jev whether it breaks server rules, and a deterministic policy turns the answers into flags, deletions or timeouts.
- Stars
- 0
- Language
- Go
- Reading time
- 2 min
- Published by
- Community
- Author
- glazk0
- Last verified
- Oct 2026
- Languages
- Go
- Capabilities
- Open sourceSelf-hosted
Highlights
- Reads every message in a Discord server and asks Jev whether it breaks the rules, converting model answers to actions with a deterministic policy.
- Jev sees context beyond the text: the author's account age, how long they have been a member and their recent messages.
- Actions are a flag, delete or timeout, and every action is reported to the log channels each server picks with /settings.
- Ships CI and Docker workflows with a ghcr.io/glazk0/shugo image and a one-click Railway deploy template.
Watch out
README reviewed 2026-10-17 from the round-eleven capture, which is truncated inside the contents list: the quick-start commands, settings reference and licence are not in the digest, and the repository has 0 stars and no declared licence.
Questions about this entry
Short answers drawn from the linked project or page.
A context-aware Discord auto-moderation bot powered by Jev, TypeSafe's System One model. It reads messages on your server and asks Jev whether each one breaks the rules, then acts on the answer.
Every message is sent to Jev as a decision request. Jev's typed answers are then run through a deterministic policy that produces a flag, a delete or a timeout, so the model never wields unchecked power over the server.
The README says Jev also gets the author's account age, how long the author has been a member and the author's recent messages, so an old account and a brand-new one can be judged differently.
The README has a Quick start section and the repository ships a Docker workflow publishing ghcr.io/glazk0/shugo plus a Railway deploy template, but the captured excerpt is truncated before the start commands, so exact steps are not in the digest.
Three: flag for review, delete the message, or delete and apply a timeout. Every action is reported to the log channels a server selects through the /settings command.
The captured README excerpt does not say. It links to docs.typesafe.ai and calls Jev TypeSafe's System One model, but the configuration and credentials sections fall outside the digest excerpt, so this cannot be confirmed here.
The digest includes the README's opening, a feature description and the contents list, but truncates before the quick start. The repository has 0 stars, no declared licence and no benchmarks, so treat claims as the author's own.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Building a contextual brand-safety scorer on Jev from scratch.
X: A website slop detector that checks 35 tells in 243 ms
X: Breaking, golden nugget, or slop
X: A filter for reply-guy comments
More Jev resources like this
An open-source merge gateway for repositories where agents write most commits: a System One model answers five fixed questions per pull request with calibrated probabilities in roughly 300 ms, a YAML policy turns them into pass, hold or block, and a planner lands non-conflicting PRs in waves.
Jev Tools & CLIs#community#github#go
Community
haalp/mergeonePython
haalp/mergeonePythonAn open-source Discord moderation bot powered by Jev. Owners sign in to a hosted dashboard, add the bot, supply their own TypeSafe key, test in Monitor only mode, then let Jev rules log, delete or time out spam, phishing, harassment, hate and threats.
Jev Tools & CLIs#community#github#typescript
Community
i098/jev-modTypeScript
i098/jev-modTypeScriptA source-available visual UI testing agent in Go: point it at a URL, describe the test, and a six-stage pipeline drives a real Playwright browser while Jev optionally validates requests, picks DOM targets and checks outcomes, falling back to an LLM below 0.9 confidence.
Jev Tools & CLIs#community#github#go
Community
ownweights/argusGo
ownweights/argusGoA single-binary gate for Impatient Programming that fails a pull request when an experienced reviewer would ask for the change to be simplified: it asks Jev about each changed file and tells the coding agent what to fix, with no LLM or parser inside.
Jev Tools & CLIs#community#github#go
Community
tools4imps/qualmGo
tools4imps/qualmGoA safety guardrail for coding agents (Claude Code, Codex, Cursor, Antigravity, Grok) that intercepts shell commands, script executions and file writes before they run. Its neural tier can use Liquid AI d1-3B, CLM, TypeSafe Jev cloud or pure rules; a deterministic tier blocks destructive patterns in under 0.1 ms.
Jev Tools & CLIs#community#github#security
Community
Bl4ckk01/agent-guardrailPython
Bl4ckk01/agent-guardrailPythonAn unofficial Go CLI that puts Jev in a coding agent's toolbox: the agent can ask where an answer lives and read only those lines, or hand Jev a yes/no or multiple-choice call and get a calibrated verdict tuned to the cost of a wrong call.
Jev Tools & CLIs#community#github#go
Community
bragamat/jevkitGo
bragamat/jevkitGoFrom 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.