#trading

Canary — local Interactive Brokers MCP server, CLI, and risk desk. Standard builds and MCP are read/preview-only; a separate opt-in trading build provides gated CLI broker writes.

Open source BTC market prediction engine. 80-dim C11 engine, 4 live rooms, 10K AI genomes, GDELT sentiment. 300/300 grid cells closed. Zero Python.

Trading Agents — PC-98 Council Terminal: a retro anime terminal UI for the TradingAgents multi-agent LLM trading framework. Eight AI agents research, debate (SSE), and rule BUY/SELL/HOLD.

Human-in-the-loop equity research agent: SEC-filing RAG with cited evidence, deterministic risk guardrails, and live execution through Robinhood's Trading MCP

Enterprise AI Trading Platform — Multi-exchange, real-time WebSocket streaming, AI agents, portfolio management

Turn trading book/paper PDFs into backtestable systems via a three-stage Claude Code skill suite: PDF → human strategy → YAML spec → backtest

Self-hosted stock portfolio & swing-trading discipline dashboard — vanilla JS + Express + Postgres, with Claude AI (thesis desk, trade audits) and an MCP server

TradingView alerts MCP server: create, list, pause, resume and delete TradingView alerts from Claude, Claude Desktop or Cursor. Pine strategy alerts with webhook support.

AI portfolio-management runtime for macOS. Watches obsessively, lacks feelings — the model advises, deterministic code decides. Experimental: paper trading only, not investment advice.

MCP server for TradeOnyx — connect your trading journal to Claude, ChatGPT or Gemini. 44 tools, JSON-RPC 2.0, hosted in Germany.

Java Agent that automates the login process for IBGateway https://www.interactivebrokers.com/campus/ibkr-quant-news/interactive-brokers-gateway-install-setup/

Pine Script v6 skills and MCP tooling for coding agents — backed by a real validator, not prose.