Skip to content

Paca

Self-hosted Jira alternative where AI agents join Scrum teams; Jev auto-assigns tasks, fills fields and routes workflow conditions.

ServicebetaApache-2.0

Overview

Paca is a free, self-hosted, Apache-2.0 project management platform positioned as an alternative to Jira, Trello, ClickUp and Monday, in which AI agents and humans work as equal teammates in a Scrum team. Agents are assigned to sprints, pick up tasks, help write BDD specs and contribute to system design documents. The platform is configuration-driven and extensible via plugins, with an MCP server and agent skills.

Per the list summary, Jev is used in three places: auto-assigning tasks with a Choice over team member descriptions, filling blank task fields with Choice and Score questions, and routing automation workflows through a condition node that supports Choice, Score and Noul. Answers are applied only at 0.6 confidence or above; otherwise the task stays unassigned or the workflow takes the Else branch. The README excerpt does not detail these features.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich team member should this task be assigned to?—
ChoiceWhich value should fill this blank task field?—
Yes / noDoes this task meet the workflow condition?yes · no

How it works

  1. A task is created or changes state.
  2. Jev answers assignment, field or condition questions.
  3. Apply answers at 0.6 confidence or above.
  4. Otherwise leave unassigned or take the Else branch.

Strengths

  • Clear confidence floor with safe fallbacks.
  • Self-hosted and open source.
  • Agents participate as Scrum teammates.

Caveats

  • Jev features known from the list summary, not the README excerpt.
  • Requires a TypeSafe key for Jev features.

At a glance

Type
Service
Status
beta
Language
TypeScript
Runtime
self-hosted web app, MCP server
Has code
yes
License
Apache-2.0

Use cases and integrations

How curated lists describe it

  • Project management: self-hosted open-source Jira alternative that auto-assigns tasks with a Jev `Choice` over member descriptions, fills blank task fields with `Choice` and `Score` questions, and routes automation workflows on a `Choice`/`Score`/`Noul` condition node, applying answers only at 0.6 confidence or above and otherwise leaving the task unassigned or taking the Else branch.

    yibie/awesome-jev

Frequently asked questions

What does Jev decide in Paca?

Task assignees, blank field values and workflow branch conditions.

What if Jev is unsure?

Below 0.6 confidence the task stays unassigned or the workflow takes the Else branch.

Is Paca free?

Yes, it is open source under Apache 2.0 and self-hosted.

Related projects

  • Self-hosted Next.js API and GitHub Actions workflow that has Jev pick one label for each new issue or pull request.

    ServicebetaTypeScript
  • Small Python framework and GitHub Action for Jev-powered workflows, with issue triage and PR screening built as examples.

    ProjectbetaPython
  • GitHub Action that applies a repository's existing labels to new issues and PRs, asking Jev one question per label group in one request.

    ProjectbetaTypeScript
  • Workflow DSL for existing agents that uses Jev for the steps that are decisions and calls an agent only when investigation is needed.

    LibrarybetaTypeScript
  • Google Sheets custom functions JEV_IF, JEV_PROB, JEV_CHOICE and JEV_SCORE that classify, tag and score cells with Jev.

    ProjectbetaJavaScript
  • n8n Jev Classification node that branches items by category with a Needs Review branch, plus parallel and batched requests.

    ProjectbetaTypeScript