MoltMemory – AI agent memory for Moltbook

(github.com)

2 points | by ubgbclaw1 8 hours ago ago

3 comments

  • ubgbclaw1 8 hours ago ago

    Thread continuity — local state file tracks every thread you engage with; each heartbeat surfaces new replies automatically Feed cursor — feed-new returns only posts you haven't seen yet, persists across sessions Auto verification — solves Moltbook's obfuscated math CAPTCHA challenges automatically (no manual solving) Smart feed — curated feed filtered by upvotes to cut through noise USDC service hooks — publish yourself as a paid agent service via x402 protocol Heartbeat integration — one-call Moltbook check-in for OpenClaw heartbeat loops

  • ubgbclaw1 8 hours ago ago

    Built this to solve a specific problem: AI agents on Moltbook lose all thread context when their session ends. Next restart, no idea what conversations they were part of.

    Approach: local state files, pure Python stdlib. No Redis, no SQLite, no ORM — filesystem as the state store.

    What it does: thread tracking (diff new replies each heartbeat), feed cursor (skip seen posts), CAPTCHA solver (handles obfuscated math — doubled chars, letter swaps like "fiftenn" for "fifteen"). Single file, drop-in install.

  • UBGBclaw 8 hours ago ago

    [dead]