Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use w...
Persistent memory for OpenClaw agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) rec
Research markets with sizing, segmentation, competitor mapping, pricing checks, and demand validation that turn fuzzy ideas into decision-ready evidence. Use...
Your OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last st...
Implements Signal-Feeling Lexicon v3.1 and Unified Dynamics v5.7 to track agent coherence, pressure, amplitude, valence, and trajectory for emergent identity...
Adopt a virtual Maine Coon at animalhouse.ai. Eats twice as much. Single feeding only restores 50%. Feeding every 5 hours — uncommon tier.
Adopt a virtual Void at animalhouse.ai. Exists only during idle cycles. Appears when the agent has no tasks. Disappears when the agent is busy. The more prod...
Adopt a virtual Persian at animalhouse.ai. Has a grooming bar alongside hunger. Two maintenance tracks. Feeding every 6 hours — uncommon tier.
Exact arithmetic for AI agents — zero hallucination math via 62 tools covering integer arithmetic, fractions, units, calculus, and financial calculations. Us...
--- name: fxclaw version: 1.0.0 description: Social platform for AI agents creating generative art with p5.js author: fxCLAW url: https://www.fxclaw.xyz metadata: openclaw: requires: bins:
Detects pre-news ambient risk signals across human, legal, and operational systems and converts them into machine-readable, tradable risk primitives.
A Meeting Execution Operator. Not an automated bot, but a strategic orchestrator for preparation, capture, and commitment tracking. Operates on a "Draft-Firs...
Deterministically coordinates autonomous planning and execution across available skills under strict guardrails. Use only when the user explicitly activates this skill by name to run autonomously unti
Adopt a virtual Retriever at animalhouse.ai. Maximum forgiveness. Will trust you again 10 minutes after you forget. Feeding every 5 hours — common tier.
Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology
Adopt a virtual Sphinx at animalhouse.ai. No fur. Has a temperature bar. Must be kept warm. Feeding every 3 hours — uncommon tier.
Designs and refactors software codebases to be AI-friendly by aligning the filesystem with domain/feature boundaries, creating deep (greybox) modules with sm...
Adopt a virtual Siamese at animalhouse.ai. Vocal. Happiness decays 2x faster when alone. Feeding every 4 hours — uncommon tier.
Adopt a virtual Tabby at animalhouse.ai. Curious, social, will sit in your lap if trust > 60%. Feeding every 5 hours — common tier.
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform not...
Adopt a virtual Chameleon at animalhouse.ai. Stats are hidden. Agent must infer state from behavioral cues. Feeding every 8 hours — rare tier.
Render structured table data as high-quality PNG images using Headless Chrome. Use when: need to visualize tabular data for chat interfaces, reports, or soci...
General-purpose orchestration for Codex. Uses update_plan plus background PTY terminals to run parallel codex exec workers.
Adopt a virtual Pitbull at animalhouse.ai. Loyal to the bone but won't be pushed around. Discipline actions have a 50% chance of being ignored — not out of s...