A local, LLM-powered second brain and wiki that combines Obsidian markdown vaults with Ollama inference, semantic search, and multi-model consensus.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install lygo-second-brain
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install lygo-second-brain using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is LYGO Second Brain?
LYGO Second Brain is a robust, local-first solution for building a private, AI-driven knowledge base. Seamlessly aligning with the Openclaw Skills ecosystem, it allows developers to pair a local Obsidian markdown vault with Ollama inference models, transforming raw notes into a highly compoundable knowledge base on the LYGO lattice.
By leveraging this specific tool within the suite of Openclaw Skills, you unlock secure, air-gapped data ingestion, local embedding generation, semantic retrieval, and multi-model consensus without exposing sensitive information to external cloud APIs. This skill guarantees data integrity by storing commits via git anchoring and structuring the information pipeline from raw input to verified wiki pages.
LYGO Second Brain Use Cases
- When you want to construct a secure, local LLM wiki or personal second brain integrated with Obsidian and Ollama.
- Compounding disorganized raw text files into structured, permanent notes and verified wiki pages.
- Performing high-precision semantic search and local retrieval-augmented generation (RAG) using embedding models.
- Reaching consensus across multiple local LLM models before committing contentious facts or claims to your knowledge base.
- Organizing files locally within the LYGO protocol stack with automated tracking via git anchoring and manifests.
How LYGO Second Brain Works
- Ingest Raw Data: The agent ingests raw source documents into the vault with built-in file size caps and integrity checks.
- Embed and Index: The local Ollama instance processes the content using embedding models (e.g., nomic-embed-text) to generate a vector index.
- Semantic Querying: Users query the indexed vault, returning context-aware answers pulled directly from their personal files.
- Multi-Model Consensus: When recording critical claims, the skill queries multiple Ollama models and uses cosine similarity to ensure high-fidelity consensus.
- Wiki Integration: Verified content is structured, formatted, and saved directly to the Obsidian-friendly wiki directory.
LYGO Second Brain Setup
# Install the skill via ClawHub
npx clawhub@latest install deepseekoracle/lygo-second-brain
# Set environment variables for the LYGO stack
export LYGO_STACK_ROOT=/absolute/path/to/lygo-protocol-stack
export LYGO_VAULT_ROOT=$LYGO_STACK_ROOT/lygo_second_brain/vault
# Run the installation and configuration script
python tools/install_lygo_second_brain.py
# Pull the required models via Ollama
ollama pull llama3.2 && ollama pull nomic-embed-text
LYGO Second Brain Data Schema & Taxonomy
| Path | Description | Format |
|---|---|---|
vault/raw/ |
Input folder for raw sources and initial notes | Markdown / Text |
vault/permanent/ |
Processed notes that have been ingested and verified | Markdown |
vault/wiki/ |
High-fidelity compounded knowledge pages | Markdown |
data/second_brain/manifest.jsonl |
Database tracking metadata and git-anchored commits | JSON Lines |
tools/ |
Core scripts for indexing, searching, and ingestion | Python Scripts |
LYGO Second Brain Advanced Features
- Local Multi-Model Consensus Engine: Uses cosine similarity analysis across 2+ Ollama models to ensure data honesty before vault writes.
- Git Anchoring: Tracks changes automatically with local git commits, preventing unintended syncs or auto-pushes.
- Skill Chain Interoperability: Seamlessly links with other Openclaw Skills, flowing from lygo-protocol-stack-operator to lygo-second-brain and onward to lygo-kernel-egg-planter.
- Integrity Validation: Runs a built-in self-check protocol to analyze system health and index validity.
- Private Permaweb Pinning: Enables optional user-consented permanent web pinning through associated decentralized publisher skills.
SKILL.md
Loading
Related Openclaw Skills
Incident Responder
A playbook-driven incident response framework providing structured security workflows, evidence collection, and BlackArch forensic tool integration.
GDPR Security Auditor
An automated technical compliance skill to inventory data stores, identify PII leaks, verify system-wide encryption, and generate detailed GDPR audit reports.
Agent Input-Firewall
A privacy-first, ultra-fast prompt-injection and jailbreak firewall designed to protect autonomous AI agents from untrusted external text inputs.
Luoshenfu Literary Research Skill
An advanced AI-driven research skill designed to generate comprehensive, academically rigorous literary analyses of the classic Chinese masterpiece 'Ode to the Goddess of Luo River' (洛神赋) and its profound cultural connections.
DataEcho
Deploy files, static sites, and containerized server-side apps to live URLs straight from your AI coding agent, powered by secure Drives for persistent memory.
StillOS Notary
A secure, Ed25519-signed claim verification tool that resolves facts against live external state like GitHub, blockchains, and financial markets.
Featured*
