AI-powered credit card research and award redemption. Live data via Brave Search, PointsYeah flight and hotel search — every command outputs clean JSON, built for humans and AI agents alike.
BRAVE_API_KEY is optional — mcc, flights, and hotels work fully offline. Live research commands require it. Requires Python 3.11+.
Conversational AI assistant for credit card research. Maintains entity memory across turns, supports multiple OpenAI models, and downloads full conversation history.
Learn MoreNine commands backed by live Brave Search data. Full card reports, wallet analysis, transfer partners, ROI estimates, and more — with JSON output for AI agents.
pip installLook up any merchant category code to find your best card at checkout. Generate PointsYeah search URLs for award flights and hotels. No API key needed for either — works fully offline.
See commandsFleece is a free, open-source credit card research tool built for people who take rewards seriously. Unlike chatbots that rely on stale training data, Fleece pulls live information from the web on every query — so you always get current fees, earning rates, and benefit details. The CLI is designed to work seamlessly with AI agents: every command supports --json output and reads from stdin, so it plugs into any workflow.
Agent Integration
Install once and every supported agent gains access to all 12 Fleece commands — research, wallet analysis, MCC lookup, and award redemption.
Install 12 slash commands directly into your Claude Code session. Use /fleece-wallet, /fleece-mcc, and more without leaving the terminal.
Install the agent skill to give OpenClaw or Codex full Fleece capability — card research, wallet gaps, MCC lookup, and redemption, all in one skill.
Fleece is published on ClawHub. Any agent that supports the ClawHub registry can install and use it with a single command — no git clone required.
All commands support --json output. Highlighted commands require no API key.