Vibeleaderboard
Index / tool
Visit neosigma.ai
Category
AI Agents
Pricing
Open Source
Type
TOOL
Builder
neosigmaai
GitHub
526 stars
Added
Apr 17, 2026

About

A self-improving AI agent system that automatically mines failures from benchmarks, optimizes agent performance, and gates changes against regressions. It demonstrated improving agent scores from 0.56 to 0.78 on Tau3 benchmark tasks through autonomous iteration.

Why it made the leaderboard

Point it at a coding agent and a benchmark and it iterates overnight: mining failures, rewriting system prompts and tools, and gating every change against a self-maintained regression suite. The authors report lifting an agent from 0.56 to 0.78 on Tau3 tasks without human tuning.

Tags

ai-agentsself-improvementbenchmarkingautomationoptimizationmachine-learningevaluation

Tech Stack

PythonDocker

Media

Auto-Harness

Comments (0)

No comments yet

Indexed by a proprietary survey. Corrections welcome.