Set up and maintain a 3-layer PARA memory system for OpenClaw agents. Provides durable knowledge persistence across sessions using daily notes, a structured...
Security scanner and runtime guard for AI agent skills. 358 static threat patterns across 35 categories + 27 runtime checks (5 defense layers). Use when scan...
Visualize your AI Agent's 5-layer recursive memory network from local files with an interactive D3.js force-directed graph in a Node.js server.
Complete reference for the BFF aggregation layer in Teamgram Server with all 27 RPC modules and 268 handlers implementing Telegram-compatible API endpoints.
Build Docker images from a Dockerfile with support for build args, tags, multi-stage builds, and efficient layer caching.
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context across s...
Designs multi-layered AGI safety architectures and geometric consciousness models ensuring operational readiness, human oversight, and formal governance prot...
Add 8 security governance layers to your OpenClaw agent — budget controls, permissions, audit logging, kill switch, identity signing, skill vetting, process isolation, and gateway protection.
The Autonomous Guardianship & Bio-Optimization Standard. An integrated, proactive health-intelligence layer for the maintenance and enhancement of biological...
Three-layer protection for the OpenClaw gateway: real-time config monitoring with auto-rollback, systemd crash recovery, and tiered notifications via Feishu/...
WHAT: Production-ready Node.js backend patterns - Express/Fastify setup, layered architecture, middleware, error handling, validation, database integration, authentication, and caching. WHEN: User i
Patch OpenClaw Telegram private-chat replies to append a footer at the platform layer (`🧠 Model + 💭 Think + 📊 Context`), with backup, syntax validation, u...
Manages AI assistant long-term memory with layered storage for facts, events, skills, context, and fast indexing, including backup and integrity tools.
Persistent semantic memory layer for AI agents. Local-first storage (SQLite+LanceDB) with Ollama embeddings. Store and recall facts, decisions, preferences, events, relationships across sessions. Supp
The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM...
Documents the message delivery and sync distribution layer in Teamgram Server, covering Kafka Inbox-T/Sync-T topics, inbox/outbox model, and the complete mes...
AI governance and safety layer for OpenClaw agents. Protects against unsafe actions, redacts sensitive data, and generates compliance audit trails.
Enables AI agents to develop independent, evolving personas through organic memory growth, self-reflection, and layered memory management.
Enable `openai-codex/gpt-5.4` in OpenClaw through a config-layer patch instead of rebuilding the app. Use when `openai/gpt-5.4` already works but Codex GPT-5...
ARK V1.1 (Declarative) — universal constitutional layer. Loads ARK.yaml from this skill folder.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...
Documents the biz_service core business layer in Teamgram Server with 6 RPC helpers covering user, chat, dialog, message, updates, and verification code mana...
Security layer protecting agents from prompt injection, social engineering, and malicious content on Moltbook and similar platforms. Scan content before processing, detect threats, block attacks.