neosigmaai/auto-harness
Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.
Repository profile
Open-source framework for agentic quantitative finance research.
Tracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-06-19 22:38
1 capture since 2026-06-19
Stars from baseline 0
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-06-19 22:38
pyproject.toml
python ecosystem,
5 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
Nearest indexed repositories by embedding similarity.
Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.
autonomous harness engineering
Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN
Self-tuning multi-agent AI trading system. 8-source signal fusion (Polymarket + Kalshi + 10 ML models incl. Kronos foundation model), Bull/Bear/Judge debate on Claude Opus 4.7, Portfolio Manager gate.
Market-making strategy that placed #2 in Paradigm's Prediction Market Challenge. 110 iterations, 8 hours.
This repo powers my experiment where ChatGPT manages a real-money micro-cap stock portfolio.