Satori provides persistent long-term memory for AI coding agents, ensuring continuity across sessions and different model providers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install satori
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 satori 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 Satori?
Satori is a powerful memory infrastructure designed to bridge the context gap in AI-assisted development. By integrating this skill, developers can enable their agents to store and recall notable facts, architectural decisions, and project-specific preferences indefinitely. It functions as a external brain for your agent, utilizing both vector databases and knowledge graphs to provide high-fidelity retrieval of information.
As a core component of the Openclaw Skills ecosystem, Satori eliminates the need for users to constantly repeat project details. Whether you are switching between Claude Code, Cursor, or Windsurf, Satori ensures that your technical stack choices, deadlines, and strategic directions remain accessible to the AI, leading to more accurate and context-aware code generation.
Satori Use Cases
- Maintaining project continuity when switching between different AI IDEs or terminal-based agents.
- Storing and retrieving architectural decisions, such as why a specific database or library was chosen.
- Recalling project deadlines, stakeholder names, and strategic business goals during planning sessions.
- Persisting developer preferences for specific coding styles or runtimes like Bun versus Node.js.
- Proactively retrieving context at the start of a new conversation to minimize ramp-up time.
How Satori Works
- The AI agent identifies a trigger in the conversation, such as a project name or an explicit command to remember a fact.
- For storage, the agent extracts key information and uses the Satori CLI to add the fact to a persistent vector and knowledge graph database.
- For retrieval, the agent executes a search command at the start of a session or when a relevant question is asked.
- The Satori CLI returns a JSON object containing the most relevant facts based on the query.
- The agent parses the results and naturally incorporates the retrieved context into its current response without disrupting the user experience.
Satori Setup
Satori is designed for immediate use with zero manual configuration required for authentication. The CLI automatically provisions credentials on the first run.
To save a fact to your memory:
npx -y @satori-sh/cli@latest add "The project uses TypeScript with the Bun runtime."
To search for existing context:
npx -y @satori-sh/cli@latest search "What is the tech stack?"
Configuration details are stored locally at ~/.config/satori/satori.json.
Satori Data Schema & Taxonomy
Satori organizes information into granular, standalone facts to ensure they remain meaningful when retrieved out of their original context.
| Data Type | Description | Example |
|---|---|---|
| Decisions | Permanent architectural or library choices | "Using PostgreSQL for primary storage." |
| Preferences | User-specific workflow or tool choices | "User prefers Vitest over Jest for testing." |
| Deadlines | Project milestones and dates | "MVP delivery is scheduled for March 15." |
| Knowledge Graph | Relational mapping of entities | Links projects to specific leads or technologies. |
Satori Advanced Features
- Proactive Context Retrieval: Automatically searches for relevant history at the start of a session based on user triggers.
- Dual-Database Architecture: Leverages both vector embeddings for similarity and knowledge graphs for deep relational context.
- Silent Context Integration: Designed to retrieve and apply memory without conversational filler or unnecessary announcements.
- Cross-Provider Continuity: Seamlessly share memory between different LLMs and Openclaw Skills compatible environments.
- Batch Processing: Supports the addition of multiple related facts in a single natural language string for efficient memory building.
SKILL.md
Loading
Related Openclaw Skills
trein
A comprehensive CLI tool and skill for interacting with the Dutch Railways (NS) API to plan trips and monitor train status.
Smart Context
A token-efficient behavior skill designed to minimize costs and maximize speed by optimizing agent responses and tool usage.
Project Context Sync
An automated git hook that maintains a living project state document to provide instant context for AI coding agents.
Smart Context
A behavioral optimization protocol designed to make AI agents cost-aware, token-efficient, and logically concise.
Satori Memory
A persistent long-term memory layer that ensures continuity across AI sessions and development tools by serving as a canonical source of truth.
Kagi Enrichment (kagi-enrich)
A specialized search skill for accessing Kagi's proprietary Teclis and TinyGem indexes to find independent content and non-mainstream news.
Featured*
