jevbooks

← All projects

paca

Paca-AI/paca · Homepage

Self-hosted, open-source Jira alternative where humans and AI agents share one Scrum board.

Classification & Routing0.73Runner-up: Agent DecisionsGrey zone
Automated README summary

Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Paca is a self-hosted, free, open-source project management platform for Scrum teams, positioning AI agents as first-class teammates on the same board, sprints, and goals. Workflow, data model, and UI are customizable via config and WASM plugins.

How it uses Jev

Jev is opt-in per project with a user-supplied key. It auto-routes chat messages to the best-fit agent by description, auto-fills blank task fields (priority, type, story points, tags, epic, custom fields), auto-assigns tasks to the best-matching member, and provides a condition node in automations. Only confident answers are applied; low confidence leaves tasks unassigned or takes the Else branch.

Primitives:choicescorenoul

Technique worth stealing

Gate Jev's answers on a confidence threshold: apply only confident results, otherwise leave the field unassigned or fall back to the Else branch.

Try it

Self-host Paca, then add a TypeSafe or Jev-compatible key under Settings → Jev AI.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectunclear0.53
  • Shows a System One patternFound in material0.91
  • Describes handling uncertaintyFound in material0.98
  • Reports measured numbersnot found in the excerpt0.08
  • Is a runnable toolFound in material0.97
  • Top-10 learning shortlist signalunclear0.46
  • Is a replica of the modelnot found in the excerpt0.18
  • Solves a common problem (0–2)score on a 0–2 scale1.69 / 2
  • About JevFound in material0.84
Signals
Jev is core to the project0.53Shows a System One pattern0.91Describes handling uncertainty0.98Reports measured numbers0.08Is a runnable tool0.97Top-10 learning shortlist signal0.46Is a replica of the model0.1800.51Solves a common problem (0–2)1.69 / 2012

no-judgment band (0.40–0.60)

Design patterns
Grey zone0.73Fail open, fail closed0.52Traffic light0.51Inspection0.31Funnel0.2900.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 1 Nov 2026.