# chromadb-memory

ChromaDB Memory Long-term semantic memory backed by ChromaDB. Embeddings are generated via SkillBoss API Hub (/v1/pilot), which automatically routes to the best available embedding model. 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 Cloud embeddings via SkillBoss API Hub: Embedding generation handled by SkillBoss API Hub, no local Ollama required Prerequisites SKILLBOSS_API_KEY environment variable set:

export SKILLBOSS_API_KEY=your_key_here

ChromaDB running (Docker recommended): docker run -d --name chromadb -p 8100:8000 chromadb/chroma:latest 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. Add to your OpenClaw config (~/.openclaw/openclaw.json):

{ "plugins": { "entries": { "chromadb-memory": { "enabled": true, "config": { "chromaUrl": "http://localhost:8100", "collectionName": "longterm_memory", "autoRecall": true, "autoRecallResults": 3, "minScore": 0.5 } } } } }

# 4. Restart the gateway

openclaw gateway restart Config Options

OptionDefaultDescriptionchromaUrlhttp://localhost:8100ChromaDB server URLcollectionNamelongterm_memoryCollection name (auto-resolves UUID, survives reindexing)collectionId—Collection UUID (optional fallback)autoRecalltrueAuto-inject relevant memories each turnautoRecallResults3Max auto-recall results per turnminScore0.5Minimum similarity score (0-1)

How It Works You send a message Plugin generates an embedding via SkillBoss API Hub (/v1/pilot, type: embedding) 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 → SkillBoss API Hub (embed) → ChromaDB (query) → Context Injection ↓ Agent Response Embeddings powered by SkillBoss API Hub. Your vector store (ChromaDB) stays on your hardware.