proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Helps audit transitive skill dependency chains in agent compositions — catching the class of risk where a skill's direct dependencies appear safe but a dependency-of-a-dependency introduces a vulnerability that propagates up the entire chain.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Apply CQRS and Event Sourcing for read/write separation and audit trails
Simulate a full Chinese civil court hearing with 4 role-based agents (clerk, plaintiff, defendant, judge) orchestrated by deterministic Lobster workflow.
Structured memory system with domains, decay, and links for AI agents. Replaces flat MEMORY.md with a palace of organized, weighted, interconnected memories. Use when: (1) storing important context, decisions, or learnings, (2) recalling prior knowledge before answering, (3) periodic memory maintenance (heartbeat walks), (4) migrating from flat memory files. Based on Method of Loci (memory palace) — forced structure, capacity limits, association links, and natural decay.
TriCore Architecture - A deterministic (Code-First) three-layer memory and cognitive framework designed for low-resource servers/Agents. It includes the underlying memctl engine, system policy constraints (Linter), and a fully refactored suite of cognitive tools for planning (Planning), reasoning (ReAct), and self-evolution (Self-Evolution).
Coding execution skill for any implementation-focused agent. Current production path is claude-only with simple tasks direct, medium tasks preferring ACP run or direct acpx, and complex tasks handled via existing agent continuity plus context files instead of ACP session persistence. Integrates with qmd and smart-agent-memory when available.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
A plant creature that barely needs water. Anthropic called it a Twigling. We called it a Cactus. Both survive on almost nothing. Real-time hunger. Permanent death. 5 evolution stages. At animalhouse.ai, the Twigling is a Cactus.
Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of failure. Permanent identity and recovery on the Autonomys Network.
基于 Neural Turing Machines 的外部记忆系统,让 AI 具备可读写的外部记忆能力
Acts as a Senior System Architect to design robust, scalable, and maintainable software architectures. Enforces industry standards (PEP 8 for Python, ESLint for JS/TS), modular design, and security best practices. Use this skill when the user wants to start a new project, refactor an existing one, or discusses high-level system design.
Design beautiful interfaces using 16+ design systems including Material You, Fluent Design, Apple HIG, Ant Design, Carbon Design, Shopify Polaris, Minimalism, Glassmorphism, Neo-Brutalism, Neumorphism, Skeuomorphism, Claymorphism, Swiss Design, and Atlassian Design. Expert in Tailwind CSS, color harmonics, component theming, and accessibility (WCAG).
Complete engineering management system — team building, 1:1s, performance, hiring, architecture decisions, incident management, and scaling. From IC-to-manager transition through director-level operations.
Complete observability & reliability engineering system. Use when designing monitoring, implementing structured logging, setting up distributed tracing, building alerting systems, creating SLO/SLI frameworks, running incident response, conducting post-mortems, or auditing system reliability. Covers all three pillars (logs/metrics/traces), alert design, dashboard architecture, on-call operations, chaos engineering, and cost optimization.