shared-brainShared persistent memory layer across multiple AI agents. Use when setting up a multi-agent workspace for the first time, when an agent discovers a permanent...
Install via ClawdBot CLI:
clawdbot install ohernandez-dev-blossom/shared-brainGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 7, 2026
A DevOps team uses multiple AI agents to manage cloud infrastructure. When one agent discovers a change in deployment configuration (e.g., Vercel migration), it writes the fact to the shared brain, ensuring all agents stay synchronized without manual updates.
In a large software project with several AI agents handling different modules (frontend, backend, database), architectural decisions like renaming a repository or changing a branch strategy are propagated across all agents via the shared brain, preventing conflicts and stale information.
Marketing AI agents managing multiple campaigns across platforms update the shared brain with permanent channel decisions (e.g., 'Discord: SKIP 3rd party links'). This ensures all agents avoid banned channels and maintain consistent campaign execution.
Security AI agents discover a new threat indicator or vulnerability that affects all agents. The finding is written to the shared brain, prompting other agents to adjust their behavior (e.g., blocking certain IPs) and ensuring a coordinated response.
When setting up a new AI agent workspace, the shared brain provides a single source of truth for initial facts like project structure, team decisions, and infrastructure details, enabling all agents to start with consistent knowledge.
Offer basic shared brain functionality for free with limited memory size (e.g., 8KB). Premium subscribers get expanded memory, priority curation, and advanced conflict resolution features.
License the shared brain package to enterprises for use in their private, on-premise AI agent workspaces. Includes dedicated support, custom integrations, and security audits.
Charge per fact written to the shared brain or provide a tiered pricing based on the number of agents. Includes a curation service that manually reviews and resolves conflicts for an additional fee.
💬 Integration Tip
Start by running `sb-install.sh --dry-run` to preview changes to AGENTS.md and HEARTBEAT.md before applying. Ensure each agent's AGENTS.md includes the startup read line `cat ~/clawd/memory/shared-brain.md` and only write permanent architectural facts to the queue, never temporary state.
Scored May 7, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...