A local-first brain management CLI for capturing, querying, and synchronizing immutable memory chains across AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memphis-cli
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 memphis-cli 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 Memphis CLI?
Memphis CLI is a powerful tool designed to manage a local-first brain, serving as a persistent memory layer for AI agents. As a key part of the Openclaw Skills ecosystem, it allows developers to maintain immutable JSONL chains that store journals, decisions, and ingested research. By prioritizing local processing through Ollama and providing robust data integrity via a vault system, it ensures that agent context remains secure, private, and highly accessible.
The skill bridges the gap between raw data and actionable intelligence by building knowledge graphs and performing semantic recall. Whether you are running a single instance or a distributed multi-agent setup, this tool provides the necessary infrastructure to keep your intelligence layers synchronized and synchronized via IPFS and encrypted messaging protocols.
Memphis CLI Use Cases
- Capturing immutable architectural decisions and project journals for long-term memory.
- Performing semantic search and RAG (Retrieval-Augmented Generation) across local documentation.
- Synchronizing state and encrypted messages between different AI agents using IPFS.
- Automating daily reflections to synthesize recent activities into high-level summaries.
- Managing sensitive API keys and secrets within an encrypted local vault.
How Memphis CLI Works
- Initialize the local environment to create the necessary directory structure and configuration files.
- Ingest or journal data into specific chains, which are stored as immutable JSON blocks.
- Generate embeddings using local models like nomic-embed-text to enable high-performance semantic search.
- Build or update the knowledge graph to establish relationships between different data points and memory nodes.
- Query the brain using the ask command, which combines semantic search with graph-based context for more accurate agent responses.
- Synchronize or push updates to external agents via IPFS for distributed collaboration.
Memphis CLI Setup
To get started with this component from the Openclaw Skills library, follow these steps:
# Initialize the Memphis environment
memphis init
# Check the health of providers and chains
memphis status
# Configure your local provider in ~/.memphis/config.yaml
# Default is Ollama at http://localhost:11434/v1
# Initialize the encrypted vault for secrets
read -rsp "Vault password: " MEMPHIS_VAULT_PASSWORD
export MEMPHIS_VAULT_PASSWORD
memphis vault init --password-env MEMPHIS_VAULT_PASSWORD
Memphis CLI Data Schema & Taxonomy
Memphis organizes data into a structured hierarchy within the ~/.memphis/ directory to ensure reliability and speed.
| Component | Storage Type | Description |
|---|---|---|
| Chains | JSONL | Immutable blocks of memory (journal, ask, decision). |
| Config | YAML | Provider settings, model definitions, and integration keys. |
| Embeddings | Vector DB | Local vector storage for semantic search and recall. |
| Vault | Encrypted Binary | AES-256-CBC encrypted storage for sensitive credentials. |
| Graph | JSONL Nodes | Metadata representing the relationships between memory blocks. |
Memphis CLI Advanced Features
- Encrypted Messaging: Zero-config, AES-256-CBC encrypted communication between agents using Pinata and IPFS.
- Knowledge Graph Construction: Automated generation of nodes and edges from existing memory chains for deeper context.
- Share-Sync: Bi-directional synchronization of shareable memory blocks via IPFS 0.27.0+.
- File Watchers: Background daemons that monitor specific paths to automatically ingest file changes into the brain.
- Automated Reflections: Periodic deep-dive analysis (daily/weekly) to consolidate memory and identify patterns.
SKILL.md
Loading
Related Openclaw Skills
Teamclaw
A high-performance Agent subsystem designed for complex multi-agent orchestration, automated scheduling, and real-time visual monitoring.
Debug Checklist
A systematic debugging framework that automates error detection to drastically reduce bug recurrence and troubleshooting time.
birdx
A high-performance X/Twitter CLI that bypasses API requirements by reading Chrome cookies directly from disk for seamless data extraction.
Self-Improving Memory Skill
A sophisticated memory layer for OpenClaw that enables persistent, cross-session learning while maintaining strict project-based isolation and privacy.
TeamClaw
A high-performance multi-agent orchestration subsystem featuring the OASIS collaboration engine, automated computer use, and social platform integrations.
Oura API Complete Export
A professional-grade data extraction tool that automates Oura Ring OAuth2 authentication and exports all available v2 user collection datasets to raw JSON.
Featured*
