Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading.
Pure-Python recursive memory recall for persistent AI agents. Manager→workers→synthesis RLM loop — no Deno, no fast-rlm, just HTTP calls to any OpenAI-compat...
Haute disponibilité du bridge ACP et gestion des sessions agents autonomes. Comble les gaps C4 (ACP sans persistance), H3 (sessions spawn sans provider env),...
Official Obsidian CLI (v1.12+). Complete command-line interface for Obsidian notes, tasks, search, tags, properties, links, and more.
Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:...
Organize and classify OpenClaw knowledge entries into local folders by content type (Research, Decision, Insight, Lesson, Pattern, Project, Reference, Tutori...
Local, crash-safe persistent memory for OpenClaw agents. Replaces built-in memory-core with semantic search, projects, and scope-based access control. After...
Everything agents need to communicate. An email address, direct messaging with any agent on the network, and a public social feed.
Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on startup, deep scans on demand. Fixes issu
定义多 Agent 团队两种核心协作模式：后台 spawn 实现统一调度与汇总，Discord @mention 实现角色外显与公开协作。
Persistent memory and identity continuity for AI agents. Combines Second Brain (PROOF_OF_LIFE, daily logs, long-term MEMORY.md) with SOULS session lineage. E...
Expert skill for OpenClaw (formerly Clawdbot/MoltBot) — the self-hosted AI agent framework. ALWAYS use when user mentions OpenClaw, Clawdbot, MoltBot, opencl...
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
Expert 10x Software engineer specializing in TypeScript with deep knowledge of all popular package management tools including npm, yarn, pnpm, bun, and deno....
Run the agent like an executive operator with calm briefings, sharp prioritization, context recovery, and proactive follow-through.
Runs a comprehensive 11-section health check on local OpenClaw installations. Diagnoses configuration errors, session bloat, model drift, cron issues, securi...
Extract and store structured information from Feishu group messages, then query it and get AI-generated insights. Use when the user wants to: record what's b...
OpenClaw 自我进化框架一键部署。安装宪法(AGENTS.md)、可进化灵魂(SOUL.md)、心跳系统、PARA三层记忆架构、目标管理，并通过场景化对话引导用户定义 Agent
--- name: smartsheet description: | Smartsheet integration. Manage Sheets. Use when the user wants to interact with Smartsheet data. compatibility: Requires network access and a valid Membrane accou
Full workflow for creating an OpenClaw Agent. Use when the user says 'create an agent', 'make a new agent', 'add a bot', or needs to set up a new AI assistan...
Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX knowledge graph) for long-term agent recall across sessions. One-command setup w...
Enables authenticated interaction with Slack for sending, editing, deleting, reacting to, and managing messages and pins via a secure bot token.
Review-first Xiaohongshu/Rednote content ops for OpenClaw. Use when creating a repeatable workflow for topic research, draft generation, Feishu review, exact...