hummingbot

Step-by-step guide for building autonomous trading agents through 5 phases: design, routine, strategy, dry-run, live.

Create or edit Python routines for market analysis, monitoring, and data visualization. Use when the user asks to create, modify, or fix a routine in the routines/ folder.

Find Cross-Exchange Market Making (XEMM) opportunities by comparing order book depth and liquidity across exchanges. Identifies pairs where one exchange has thin liquidity (ideal for quoting) and another has deep liquidity (ideal for hedging).

Find arbitrage opportunities across exchanges by comparing prices for fungible token pairs like BTC/WBTC and USDT/USDC.

Developer skill for running Hummingbot and Gateway from source, building wheel and Docker images, and testing against Hummingbot API running from source. Use this skill when a developer wants to build, run, or test Hummingbot components locally.

OpenClaw cron job that delivers hourly Hummingbot status updates to your chat — API health, Gateway container, active bots/controllers, executors, and portfolio balances.

Run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API.

Check which exchanges work from your location and search for tokens with trading rules (min order size, price increment, order types).

How total_amount_quote and initial_positions define a controller's isolated capital — the budget a single pmm_mister controller trades with, and how to seed it with base assets you already hold so each controller is independent from the wider portfolio.

Run the MM bot status report: running bots, open/hold-mode positions, closed position breakdown (TP/SL/Early/Hold), PnL, volume, and error summary.

Ready-to-deploy pmm_mister config profiles (aggressive / balanced / conservative) — full parameter coverage including spreads, effectivization times, tolerance, order types, skew, and global TP/SL.

End-to-end playbook for deploying a pmm_mister bot on a token — regime analysis, profile selection, config creation, and bot deployment.

On hyperliquid_perpetual, tokenized perp contracts (equities/pre-IPO names like SPCX-USD) are issued by a provider and require an issuer prefix in the trading pair (e.g. XYZ:SPCX-USD, not SPCX-USD).

Create and operate autonomous trading agents the minimal way — create the agent from just its role + purpose, prove it's alive by consulting it, then progressively improve it with routines and (optionally) a loop strategy.

The single reference for writing Condor routines — fetching Hummingbot data, parallel calls, reports/charts, continuous loops, and candlestick charts. Routes to a companion file per topic.

AI-driven log analysis for active bots, executors, and gateway — anomaly detection and failure pattern recognition over Hummingbot logs, for both real-time monitoring and retrospective diagnostics.