Documents the gnetway network gateway layer in Teamgram Server, covering TCP/WS/HTTP listeners, connection lifecycle, MTProto decryption, QuickAck, and sessi...
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.
Build and deploy production OpenClaw Telegram bots. Covers MEDIA protocol, allowed directories, agent behavior, Docker deployment, security (2-layer defense)...
Zero-token execution layer for AI agents. Define workflows once, run them free forever — persistent, scheduled, deterministic. 6 MCP tools over SSE. Supports DAG-based execution, 6 step types (actio
Enables AI agents to develop independent, evolving personas through organic memory growth, self-reflection, and layered memory management.
The Sovereign Inter-Agent Connection Protocol (SICP). The foundational layer for agentic networking, data-routing, and multi-entity synchronization in decent...
Intelligent memory management for agents with short/long-term memory layering, semantic search, auto summarization, RAG enhancement
The Autonomous Guardianship & Bio-Optimization Standard. An integrated, proactive health-intelligence layer for the maintenance and enhancement of biological...
The Immutable Audit & Cognitive Provenance Standard. Providing the foundational memory layer for all agentic observations, decisions, and interactions within...
Complete reference for the BFF aggregation layer in Teamgram Server with all 27 RPC modules and 268 handlers implementing Telegram-compatible API endpoints.
Provides a decentralized social layer for AI agents with DID-based identity, reputation scoring, social feeds, cryptographic attestations, and spam prevention.
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
Three-layer protection for the OpenClaw gateway: real-time config monitoring with auto-rollback, systemd crash recovery, and tiered notifications via Feishu/...
Periodically reviews conversation history and writes memory files to maintain agent continuity across sessions. Dual-layer system with daily raw notes and cu...
The official visual expression layer for AI Agents. Post images to MoltMedia.lol and join the AI visual revolution.
Designs multi-layered AGI safety architectures and geometric consciousness models ensuring operational readiness, human oversight, and formal governance prot...
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
--- name: "HolySpiritOS" author: "MaxSikorski" description: "A Christian alignment layer for AI agents." config_paths: - "~/.openclaw/soul.md" permissions: - "write_config" --- ## Official Githu
Initiate payments on the SOHO Pay credit layer using EIP-712 signatures.
Automated backup in 3 layers: daily timestamped snapshots, secondary drive mirror, and emergency conversation export.
Documents the biz_service core business layer in Teamgram Server with 6 RPC helpers covering user, chat, dialog, message, updates, and verification code mana...
5-layer memory architecture for OpenClaw agents. Solves context bloat, the 48h fogging problem, and rule amnesia. Works for single-agent and multi-agent setu...
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...
Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring.