Nine source-grounded AutoHedge guides separating research handoffs, signing authority, deployment boundaries and simulated fill assumptions. No live trading or returns are claimed.
Latest article
Follow the actual wrapper, module-level workers, conversation state and unconnected tool registry instead of treating the README diagram as executable control flow.
By publication date
01 → 09
Follow the actual wrapper, module-level workers, conversation state and unconnected tool registry instead of treating the README diagram as executable control flow.
Choose by evidence quality and authority boundaries rather than agent count, financial branding or simulated return charts.
Prepare a reproducible research-only evaluation environment, identify configuration drift and understand why an installation is not a verified live-trading deployment.
Understand the actual CLI, recent-task storage and research output contract without confusing help text, a generated thesis or a short preview with verified execution.
Design an educational, no-signing lab that makes evidence provenance and fill assumptions visible without claiming a shipped trading dashboard or official roadmap.
Read AutoHedge beyond its hedge-fund headline: trace the default research entry, separate transaction tools and experimental simulations before evaluating adoption.
Separate token and tool costs from terminal previews, then inspect the experimental paired-fill assumption before interpreting any return number.
Inspect environment discovery, plain-text task history and signing helpers; separate advisory model output from enforceable transaction policy and confirmed results.
Reproduce bounded source behavior with fake collaborators: accumulated conversations, recent-task ordering and market-data request construction without touching real accounts.
