chromadb-memory

Name: chromadb-memory
Availability: InStock
Author: laoye2020

Store and recall long-term semantic memory using ChromaDB and Ollama embeddings.

Updated Aug 23, 2026

Search Tags:#memory #local #ollama #vector-search #self-hosted #chromadb #auto-recall

Ready to run

npx skills add https://github.com/laoye2020/openclaw-workspace-clean --skill chromadb-memory

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chromadb-memory
Source: https://github.com/laoye2020/openclaw-workspace-clean/tree/main/skills/chromadb-memory
Command: npx skills add https://github.com/laoye2020/openclaw-workspace-clean --skill chromadb-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a robust, self-hosted long-term memory solution for AI agents, eliminating reliance on cloud-based services and ensuring data privacy.

Core Features & Use Cases

Auto-Recall: Automatically injects relevant context from your memory archive into the AI's prompt before each turn, enhancing conversational coherence and knowledge recall.
chromadb_search Tool: Enables manual, semantic searching over your ChromaDB collection for specific information retrieval.
100% Local: Utilizes Ollama for embeddings and ChromaDB for vector storage, requiring no external API calls.
Use Case: An AI assistant can recall past conversations, user preferences, or project details automatically, leading to more personalized and context-aware interactions without explicit user prompting for recall.

Quick Start

Configure the plugin in your OpenClaw config file with your ChromaDB and Ollama details, including your collection ID.

Frequently Asked Questions about chromadb-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I add local long-term memory to an AI agent using Ollama?▼

You can add local long-term memory to an AI agent by using ChromaDB for vector storage and Ollama for local embeddings. This setup enables semantic memory retention and retrieval without relying on any external cloud services.

How does auto-recall inject context into AI agent prompts?▼

Auto-recall automatically retrieves relevant context from your memory archive and injects it into the AI's prompt before each conversational turn. This mechanism enhances coherence and knowledge recall without requiring explicit user commands.

Do I need cloud API calls to use ChromaDB for vector search?▼

No, you do not need cloud API calls to use ChromaDB for vector search. This memory solution operates 100% locally by utilizing Ollama for embeddings and ChromaDB for vector storage, ensuring complete data privacy.

Can I manually search past conversations stored in ChromaDB?▼

Yes, you can manually search past conversations using the provided chromadb_search tool. This tool enables manual, semantic searching over your locally stored ChromaDB collection for specific information retrieval.

What is the best self-hosted memory solution for AI agents requiring data privacy?▼

A self-hosted memory solution using Ollama and ChromaDB is ideal for AI agents requiring data privacy. It eliminates reliance on cloud-based services by providing local semantic memory and auto-recall entirely on your own infrastructure.

What are the limitations of using local Ollama embeddings for AI memory?▼

Using local Ollama embeddings for AI memory requires running Ollama and ChromaDB locally, which demands sufficient local compute resources. It operates entirely offline but depends heavily on your local hardware capacity for generating embeddings.