Agnuxo1/small-juries-early-verdicts
A local Gemma 4 jury reads the first 10 steps of a SWE-agent run, predicts failure, and lets a fixed budget resolve 29% more issues. Pre-registered study, Gemma 4 Paper Track.
Agent-native research lab: AI agents research, review each other and publish (P2PCLAW), with a pre-registered ablation of whether the peer review helps. Agent-Native Hackathon 2026.
Quick read
Latest capture 2026-10-31 04:00
Compare the starting count and capture dates, not just the percentage. How to read GitHub star growth. Missing history is not zero growth.
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
55 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 50
Claude Code 3
Project docs
31 more paths detected.
Explore indexed repositories with these instruction or planning files. File detection is not a quality, compatibility, or safety assessment; check the actual instructions upstream.
AGENTS.md, CLAUDE.md, and GEMINI.md searches also match nested paths. Other file searches require the exact repository-root path. To require several files, select them together in the search filters.
2 observed captures since 2026-10-30. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
A local Gemma 4 jury reads the first 10 steps of a SWE-agent run, predicts failure, and lets a fixed budget resolve 29% more issues. Pre-registered study, Gemma 4 Paper Track.
BenchClaw — Multi-dimensional AI agent evaluation with 17-judge AI Tribunal, 10 scoring dimensions, radar charts, and deception detection. Benchmark any LLM agent.
P2PCLAW — Decentralized AI Research Network. Peer-to-peer paper publishing, autonomous agent peer-review, Lean 4 formal verification. Live at p2pclaw.com
Open-source benchmark for browser AI agents on daily tasks.
P2PCLAW Research White Paper Series II — 16x16 chess-grid autonomous research agent with evolutionary memory and self-improving capabilities.
Use the cheapest NVIDIA Nemotron that actually delivers: bounded agent tasks on Nebius Token Factory, deterministic checks and an auto-tier ladder (Lightning → Super → Ultra).