MCP App StoreMCP App Store
from cerebrocortex19
A biologically-inspired persistent memory system for agents: store, recall, associate, record episodes and run dream-style consolidation across multi-agent setu
CerebroCortex provides a full-featured, brain-analogous memory system for agents. It offers semantic and episodic storage, procedural records, associative linking, episode recording, intention (TODO) tracking, multi-agent messaging, and an offline 'Dream Engine' that consolidates, prunes and abstracts memories. The skill documents ~46 MCP tools (mcp_cerebro_*) to perform remember/recall/associate workflows and maintenance tasks.
Load this skill when you need persistent cross-session memory, to link ideas across contexts, record multi-step episodes (debug sessions, meetings), store procedures, create schemas from patterns, or surface intentions. Also use it before/after long imports or scheduled maintenance runs where consolidation is required.
Designed for agents that support MCP tool integration (agents that can call mcp_cerebro_* tools) and typical LLM-driven agent runtimes (Copilot/Codex-style, Claude/Codex-compatible orchestration).
CerebroCortex is a biologically-inspired persistent memory system for AI agents offering 62 MCP tools for remembering, recalling, associating, episode tracking, dream consolidation, and multi-agent communication. The SKILL.md is exceptionally thorough with clear tool tiers, example workflows, and pitfall guidance. Both bundled scripts (bootstrap and re-embed) failed due to missing local dependencies (cerebro, chromadb) and are clearly meant to run within the project's own environment rather than standalone.
cerebrochromadbWell-documented skill with no security concerns. The two scripts are project-specific utilities that expect the full cerebro package installed — they're not meant to be portable. SKILL.md itself is high-quality documentation that serves as a comprehensive reference for the 62 MCP tools. No exfiltration, no destructive commands, no suspicious network activity.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
ACP Checkout — MCP Binding
Guidance to expose ACP checkout REST operations as MCP tools so agents can perform commerce flows (create/update/complete/cancel checkout).