Memori

Troubleshooting

Quick fixes for the most common Memori issues.

Installation

Python

If pip install memori fails — Requires Python 3.10+. Run python --version to check, then pip install --upgrade pip && pip install memori.

TypeScript

If npm install @memorilabs/memori fails — Requires Node.js 18+. Run node --version to check, then update Node.js and retry.

Module resolution errors — Ensure your tsconfig.json uses "moduleResolution": "node" or "bundler". The SDK ships ESM with TypeScript declarations.

API Key Issues

Invalid or missing API key — Set the MEMORI_API_KEY environment variable:

export MEMORI_API_KEY="your-memori-api-key"

Quota exceeded — Upgrade your account at app.memorilabs.ai/settings/billing.

No Memories Being Created

  1. Register your LLM client — conversations aren't captured without registration:
Register Client
client = OpenAI()
mem = Memori().llm.register(client)
  1. Set attribution before LLM calls — without it, no memories are stored:
Set Attribution
mem.attribution(entity_id="user_123", process_id="my_app")

Recall Returns Empty

  • Verify entity_id matches what was used when memories were created
  • Increase limit: mem.recall("query", limit=10)
  • Lower threshold: mem.config.recall_relevance_threshold = 0.05

Performance

Network timeouts — Increase timeout: mem.config.request_secs_timeout = 10 and retries: mem.config.request_num_backoff = 10.

Debug Logging

Enable debug logging to inspect request flow, attribution, and augmentation behavior when troubleshooting missing memories or API errors. Use it temporarily in development, since logs can include sensitive request metadata.

Debug Logging
import logging
logging.basicConfig(level=logging.DEBUG, format="%(asctime)s | %(name)s | %(levelname)s | %(message)s")

from memori import Memori
mem = Memori()

Getting Help

Include your language, runtime version (Python/Node.js), Memori version (pip show memori or check package.json), and full error trace.