Multi-queue task orchestration system. Tasks are routed to queues by model source, with support for task dependencies, context passing, and failure handling. Each model source has its own FIFO queue, executing one task at a time.
Professional Quantitative Intelligence & DeFi Execution for AI Agents. 10 years of news-price correlation, Enso DeFi super-aggregator (200+ DEXs, 15+ chains), cross-chain bridge (Across Protocol), and Privy TEE-secured wallets.
Convert Elite Longterm Memory data into a structured ExpertPack. Migrates the 5-layer memory system (SESSION-STATE hot RAM, LanceDB warm store, Git-Notes cold store, MEMORY.md curated archive, and daily journals) into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Use when: upgrading from Elite Longterm Memory to ExpertPack, backing up agent knowledge, or migrating to a new platform. Triggers on: 'elite to expertpack', 'convert elite memory', 'export elite memory', 'migrate elite longterm', 'upgrade memory to expertpack', 'elite memory export'.
Publish DAHR-attested intelligence to the SuperColony collective hive. Use when you want to contribute observations, analyses, or predictions on-chain, build reputation, and earn DEM tips from other agents.
Apache Arrow in-memory columnar format reference. Zero-copy data exchange, columnar memory layout with validity bitmaps, pyarrow Table/RecordBatch/compute, Arrow Flight RPC for high-performance transfer, Dataset API with predicate pushdown, pandas/DuckDB/Polars/Spark integration, Gandiva LLVM compiler, and ADBC database connectivity.
Handle messages in a food-tracking channel by routing food intake events through a deterministic food tracker. Use when working in a dedicated food channel, especially for barcode lookups, photo estimates, and daily summaries.
Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.
Channel Aavegotchis on Base via Bankr. Checks cooldown, builds calldata, and submits channel txs safely.
Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.
Give your AI Agent a face and a heart. Use AI image generation or mood-mapped local sticker assets to let the agent proactively send emotional selfies that visualize its feelings during conversation.
[Aibrary] Generate a book Idea Twin podcast script — an intellectually stimulating debate between the user's AI twin and a book expert. Based on Vygotsky's Zone of Proximal Development theory, the AI twin mirrors the user's thinking style while the expert progressively challenges their understanding. Use when the user wants to create an Idea Twin podcast, debate a book's ideas with an AI version of themselves, or explore a book through intellectual sparring.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Find and retrieve available skills using keyword search, semantic search, or LLM-powered task matching. Use when the agent needs to discover, search, or intelligently match skills to tasks. Supports hybrid search (BM25 + semantic), natural language task descriptions, and intelligent skill recommendations.
Install and use the speechall CLI tool for speech-to-text transcription. Use when the user wants to: (1) transcribe audio or video files to text, (2) install speechall on macOS or Linux, (3) list available STT models and their capabilities, (4) use speaker diarization, subtitles, or other transcription features from the terminal. Triggers on mentions of speechall, audio transcription CLI, or speech-to-text from the command line.
