Framework turns a trader’s transcripts into a Python paper-trading bot
tom_doerr · x · 2026-07-22
A framework that turns a trader’s recorded thinking into a Python-based screening and paper-trading bot.
- It ingests transcripts from sources like YouTube videos, articles, and tweets.
- The system distills the trader’s strategy into pass/fail gates, then runs those gates as a live screener on Hyperliquid.
- An optional LLM “agent” can sit on top and review each setup against a philosophy document written in the trader’s own voice.
- The repo frames trading as a judgment pipeline: content -> strategy doc -> scanner (gates) -> paper trader, with an optional philosophy doc -> agent layer.
More from coding & agent
- OpenFPM CUDA-style kernels now run on Apple Silicon GPUs via Metal — Scobleizer · 2026-07-22
- Sol Pro built a 44-file handoff kit after a voice-first coding workflow — RileyRalmuto · 2026-07-22
- AI Dev Tools Zoomcamp opens with spec, context, loop, and graph engineering — Al_Grigor · 2026-07-22
- New paper defines four conditions that turn an LLM into a coding agent — alex_verem · 2026-07-22
- Obsidian’s 5 official agent skills teach Claude native notes, Bases and JSON Canvas — FinanceYF5 · 2026-07-22
- MCP lets Claude read and write Obsidian vault notes without copy-paste — FinanceYF5 · 2026-07-22