Cérebro
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Cérebro — Obsidian Vault for AI-Assisted Development
A structured Obsidian vault designed to give AI coding agents (opencode, Claude, Cursor) persistent memory, project context, and operational knowledge across sessions.
What is this?
Cérebro is a knowledge management system that bridges the gap between AI coding sessions. Instead of losing context between conversations, your vault retains:
Project context — stack, architecture, decisions, current state
Session logs — what was done, what's pending, what's next
Technical decisions — ADRs with rationale and alternatives
Patterns & lessons — failure patterns, prevention checklists, reusable knowledge
Operational runbooks — deploy, debug, rollback procedures
Related MCP server: Speakeasy Docs MCP
Quick Start
# Clone this repo
git clone https://github.com/ricardopiresqa/cerebro.git
# Open in Obsidian
# File → Open Vault → select the cloned folder
# Set up environment
cp .env.example .env
# Edit .env with your pathsVault Structure
Cérebro/
├── _templates/ ← Templates for projects, ADRs, runbooks, lessons
├── 0_inbox/ ← Drafts and uncategorized ideas
├── 1_projetos/ ← Active projects (CONTEXT.md + DECISIONS.md + CURRENT.md)
├── 2_knowledge/ ← Knowledge base (guides, studies, career)
├── 3_playbooks/ ← Reusable process playbooks
├── 4_runbooks/ ← Operational runbooks
├── 5_adrs/ ← Architecture Decision Records
├── 6_postmortems/ ← Incident postmortems
├── 7_research/ ← Research and proofs of concept
├── 8_patterns/ ← Code/architecture patterns and lessons
├── 9_standards/ ← Vault conventions
└── 10_glossary/ ← Technical glossaryHow It Works
Project Files
Every project gets three mandatory files:
File | Purpose |
| Stack, structure, repo URL, what it is |
| Technical decisions (chronological) |
| Current state, blockers, next step |
Session Lifecycle
START SESSION
1. Read CONTEXT.md + DECISIONS.md + last session log
2. Search RAG for relevant history
3. Load applicable skill
4. Work
END SESSION
5. Log session in sessoes/
6. Reindex RAG
7. Update DECISIONS.md if new decisions madeAdding a Project
Create
1_projetos/<project-name>/Add
CONTEXT.mdwith stack, structure, and repo infoAdd
DECISIONS.mdwith initial decisionsAdd
CURRENT.mdwith current stateOptionally create a ClickUp card and link it
Templates
Template | Use Case |
| Architecture Decision Record |
| Project current state |
| Technical decisions log |
| Session log |
| Learned lesson |
| Operational procedure |
| Incident postmortem |
| Project onboarding checklist |
| Git hooks config |
Features
Deterministic navigation — numbered folders (0-10) for predictable structure
Fuzzy search — RAG-powered hybrid search (vector + BM25) across all markdown
AI agent integration — steering files tell agents how to behave in your vault
Session persistence — every coding session is logged with decisions and context
Self-improvement — pattern mining, failure analysis, skill effectiveness tracking
Integrations
opencode — reads vault context automatically
Obsidian — renders markdown with Dataview for dashboards
ClickUp — task management via API
RAG — hybrid search with ChromaDB + BM25
Philosophy
Your AI agent should never start from zero. Every session builds on the last.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Web search API and MCP server for developers building AI agents.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that provides a local-first RAG engine for your markdown documents. It uses a file-based Milvus vector database to index your notes, enabling LLMs to perform semantic search and retrieve relevant content from your local files.364Apache 2.0

Speakeasy Docs MCPofficial
AlicenseNot gradedqualityBmaintenanceA lightweight, domain-agnostic hybrid search engine for markdown corpora, exposed via the Model Context Protocol (MCP), optimized for serving SDK documentation to AI coding agents.9AGPL 3.0- AlicenseNot gradedqualityDmaintenanceAn MCP server that indexes documents and serves relevant context to LLMs via Retrieval Augmented Generation (RAG).36MIT
- FlicenseNot gradedqualityDmaintenanceA local RAG server using the Model Context Protocol (MCP) to allow AI assistants to query private documents with persistent memory and support for many file formats.1-