Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

WrongStack

Open-source AI coding agent with memory and specialist agents; the list notes an optional Jev dispatch classifier.

ProjectbetaMIT
View on GitHub ↗

Overview

WrongStack is a free, MIT-licensed AI coding agent written from scratch in TypeScript. It reads code, runs tools and coordinates specialist agents, with a Brain that evaluates policy decisions, SAGE for project knowledge across sessions, Kanban for work tracking and verification, a mailbox linking agents across clients, and Chimera for reviewing diffs. It installs as a single binary on macOS, Linux and Windows.

According to the list summary, it includes an optional Jev dispatch classifier for choosing among its specialist agents. The fetched README excerpt does not describe that integration, so the questions and thresholds are not documented here. Its coding loop compares completed tool results to detect repetition, and file edits can include bounded diagnostics when the LSP plugin is enabled.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich specialist agent should handle this task?(inferred)—

How it works

  1. The leader agent receives a task.
  2. Optionally, Jev classifies which specialist should take it.
  3. The specialist works; Kanban and Chimera track and review.

Strengths

  • Jev routing is optional within a full agent.

Caveats

  • Jev integration not documented in the README excerpt.
  • Large system to adopt.

Getting started

curl -fsSL https://wrongstack.com/install.sh | sh

At a glance

Type
Project
Status
beta
Language
TypeScript
Runtime
standalone CLI agent
Has code
yes
Has tests
yes
License
MIT

Use cases and integrations

How curated lists describe it

Frequently asked questions

How does WrongStack use Jev?

Per the list, as an optional classifier to dispatch tasks to specialist agents.

Is it a plugin for another agent?

No, it is a standalone coding agent.

Is it free?

Yes, open source under MIT.

Related projects

  • Helm

    Orchestrator that probes which coding agents are installed and logged in, then has Jev pick the best one for a task.

    Agent skillbetaPython
  • jev-agent-hooks

    Hooks for Claude Code, Codex and pi that use Jev to suggest a skill each turn, plus a rule gate for subagent model routing.

    HookbetaJavaScript
  • jev-claw

    OpenClaw plugin adding a jev_route tool that classifies tasks with Jev and applies routing policy as code, with optional automatic routing.

    ProjectbetaTypeScript
  • jev-pilot

    Claude Code plugin that asks Jev before each turn for reasoning effort, subagent model, strategy and skill, with a decision log.

    Agent skillbetaTypeScript
  • JevRouter

    Router that puts models, subagents, skills, MCP tools and CLIs in one candidate set and asks Jev one Choice about which handles the step.

    MCP serverbetaTypeScript
  • TriRouter

    Prompt router for Claude Code, Codex and Antigravity that picks model, effort, skill and language per request via Jev.

    ProjectbetaPython