ChromaDB Memory

Long-term semantic memory backed by ChromaDB and local Ollama embeddings. Zero cloud dependencies.

What It Does

• Auto-recall: Before every agent turn, queries ChromaDB with the user's message and injects relevant context automatically
• chromadb_search tool: Manual semantic search over your ChromaDB collection
• 100% local: Ollama (nomic-embed-text) for embeddings, ChromaDB for vector storage

Prerequisites

ChromaDB running (Docker recommended):

docker run -d --name chromadb -p 8100:8000 chromadb/chroma:latest

Ollama with an embedding model:

ollama pull nomic-embed-text

Indexed documents in ChromaDB. Use any ChromaDB-compatible indexer to populate your collection.

Install

# 1. Copy the plugin extension
mkdir -p ~/.openclaw/extensions/chromadb-memory
cp {baseDir}/scripts/index.ts ~/.openclaw/extensions/chromadb-memory/
cp {baseDir}/scripts/openclaw.plugin.json ~/.openclaw/extensions/chromadb-memory/

# 2. Get your collection ID
curl -s  | python3 -c "import json,sys; [print(f'{c[\"id\"]}  {c[\"name\"]}') for c in json.load(sys.stdin)]"

# 3. Add to your OpenClaw config (~/.openclaw/openclaw.json):

{
  "plugins": {
    "entries": {
      "chromadb-memory": {
        "enabled": true,
        "config": {
          "chromaUrl": "",
          "collectionId": "YOUR_COLLECTION_ID",
          "ollamaUrl": "",
          "embeddingModel": "nomic-embed-text",
          "autoRecall": true,
          "autoRecallResults": 3,
          "minScore": 0.5
        }
      }
    }
  }
}

# 4. Restart the gateway
openclaw gateway restart

Config Options

Option

Default

Description

chromaUrl	| ChromaDB server URL | | collectionId | *required* | ChromaDB collection UUID | | ollamaUrl |	Ollama API URL
embeddingModel	nomic-embed-text	Ollama embedding model
autoRecall	true	Auto-inject relevant memories each turn
autoRecallResults	3	Max auto-recall results per turn
minScore	0.5	Minimum similarity score (0-1)

How It Works

You send a message

Plugin embeds your message via Ollama (nomic-embed-text, 768 dimensions)

Queries ChromaDB for nearest neighbors

Results above minScore are injected into the agent's context as

Agent responds with relevant long-term context available

Token Cost

Auto-recall adds ~275 tokens per turn worst case (3 results × ~300 chars + wrapper). Against a 200K+ context window, this is negligible.

Tuning

• Too noisy? Raise minScore to 0.6 or 0.7
• Missing context? Lower minScore to 0.4, increase autoRecallResults to 5
• Want manual only? Set autoRecall: false, use chromadb_search tool

Architecture

User Message → Ollama (embed) → ChromaDB (query) → Context Injection
                                                  ↓
                                          Agent Response

No OpenAI. No cloud. Your memories stay on your hardware.