A 100% local, self-hosted long-term memory system using ChromaDB and Ollama for intelligent context injection.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install chromadb-memory
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 chromadb-memory 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 ChromaDB Memory?
The ChromaDB Memory skill provides AI agents with a robust long-term semantic storage layer. By leveraging local vector databases and embedding models, it ensures that your agent can recall past interactions and relevant documents without ever sending data to the cloud. This skill is a foundational component for privacy-focused developers building with Openclaw Skills.
It bridges the gap between ephemeral chat sessions and persistent knowledge by automatically retrieving and injecting relevant context into the agent's current workspace. Whether you are managing complex projects or building a personal knowledge base, this skill ensures your AI always has the right information at hand.
ChromaDB Memory Use Cases
- Persistent context across multiple chat sessions for complex coding projects
- Building a private, self-hosted knowledge base for sensitive internal documentation
- Reducing hallucinations by providing grounded facts from a local vector store
- Automating information retrieval for Openclaw Skills without manual search tools
How ChromaDB Memory Works
- The user sends a message to the AI agent which triggers the skill workflow.
- The system generates a vector embedding of the user's message using a local Ollama model like nomic-embed-text.
- A similarity search is performed against the ChromaDB collection to find the most relevant historical data.
- Relevant snippets that meet the similarity threshold are formatted and injected into the agent's prompt context automatically.
- The agent generates a response informed by both the immediate query and the retrieved long-term memories.
ChromaDB Memory Setup
To get started with this addition to your Openclaw Skills, ensure ChromaDB and Ollama are running locally.
- Start ChromaDB using Docker:
docker run -d --name chromadb -p 8100:8000 chromadb/chroma:latest
- Pull the required embedding model:
ollama pull nomic-embed-text
- Install the skill by copying the plugin files to your local directory:
mkdir -p ~/.openclaw/extensions/chromadb-memory
# Copy index.ts and openclaw.plugin.json to the directory
- Configure your ~/.openclaw/openclaw.json with the local URLs for ChromaDB and Ollama and restart the gateway.
ChromaDB Memory Data Schema & Taxonomy
The skill organizes data within a ChromaDB collection. It primarily manages vector embeddings and associated text metadata to support Openclaw Skills functionality.
| Field | Type | Description |
|---|---|---|
| content | String | The raw text of the memory snippet |
| embedding | Vector | 768-dimension vector generated by Ollama |
| metadata | Object | Includes source information, timestamps, and custom tags |
All data is stored in the collection specified in the configuration, defaulting to the longterm_memory collection name.
ChromaDB Memory Advanced Features
- Automatic context injection (Auto-recall) with configurable result limits per turn
- Manual semantic search via the chromadb_search tool for targeted developer queries
- Adjustable similarity scoring (minScore) to fine-tune the precision of retrieved memories
- Support for custom Ollama embedding models to optimize for specific technical data types
- Full compatibility with other Openclaw Skills for sophisticated multi-agent workflows
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Default Agent Backstory
A systematic framework for bootstrapping and maintaining stable AI agent identities through guided interviews and core context file generation.
Uptime Kuma Monitoring
A powerful CLI-driven skill to manage Uptime Kuma monitoring instances, allowing for automated status checks and monitor configuration.
Proxmox VE Full Management
A comprehensive automation skill for managing Proxmox VE infrastructure, including virtual machines and Linux containers, via its REST API.
SignalHire Profile Search & Enrichment
A comprehensive tool for Openclaw Skills to automate candidate sourcing, profile searching, and asynchronous contact enrichment via the SignalHire API.
LegalFrance
An advanced AI legal assistant providing hybrid retrieval and verifiable citations for French consolidated laws within the Openclaw Skills ecosystem.
SkillGuard
A comprehensive security auditing tool designed to scan, detect, and neutralize threats within Openclaw Skills.
METADATA
Featured*
