Stdlib-only Python CLI that orchestrates universal AI agent providers (Claude Code, Codex, Antigravity, OpenRouter, DeepSeek, Groq, local models, Aider) into a multi-agent PR review jury — debate, verify, synthesize one verdict. Local-first, secure by default.
Last commit October 25, 2026, 24 days ago.
10 GitHub stars and 0 Honeystax upvotes. Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
Starts at 6. Added: no security policy +8.
AI Agent
Multiple
Model
Multiple
Fastest way to find out if ai-jury belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/berkayturanci/ai-jury ~/.claude/agents/ai-juryRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/ai-juryNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ skills/ ├─ agents/ │ └─ ai-jury/ ← installs here └─ settings.json
ai-jury is listed on Honeystax as an Agent for Multiple, since July 20, 2026. Its code is at github.com/berkayturanci/ai-jury, with 10 GitHub stars and 4 open issues. Last commit October 25, 2026, 24 days ago. GitHub's community health check gives it 100 out of 100.
Source: GitHub repository
Source check: October 26, 2026
Upstream commit: October 25, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.