mem0ai/mem0 · critical · ValueError

MEM0_TELEMETRY must be a boolean value.

Error message

MEM0_TELEMETRY must be a boolean value.

What it means

Raised at import time of mem0.memory.telemetry when the MEM0_TELEMETRY environment variable, after the str-to-bool conversion, is not a bool. In practice os.environ.get() always returns a str (or the default 'True'), and any string is coerced via `value.lower() in ('true','1','yes')`, so this ValueError is effectively unreachable through the environment variable — it fires only if MEM0_TELEMETRY is programmatically set to a non-str/non-bool object before import (e.g. monkeypatching or mutating os.environ with an int). Because it triggers on import, it breaks every mem0 import, not just telemetry calls.

Source

Thrown at mem0/memory/telemetry.py:23

import random
import sys
import threading

from posthog import Posthog

import mem0
from mem0.memory.setup import get_or_create_user_id

MEM0_TELEMETRY = os.environ.get("MEM0_TELEMETRY", "True")
PROJECT_API_KEY = "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"
HOST = "https://us.i.posthog.com"
FEATURE_FLAGS_REQUEST_TIMEOUT_SECONDS = 0.5

if isinstance(MEM0_TELEMETRY, str):
    MEM0_TELEMETRY = MEM0_TELEMETRY.lower() in ("true", "1", "yes")

if not isinstance(MEM0_TELEMETRY, bool):
    raise ValueError("MEM0_TELEMETRY must be a boolean value.")

logging.getLogger("posthog").setLevel(logging.CRITICAL + 1)
logging.getLogger("urllib3").setLevel(logging.CRITICAL + 1)
_logger = logging.getLogger(__name__)


# Default sampling rate for hot-path OSS events. Lifecycle events always fire at 100%.
# Override via MEM0_TELEMETRY_SAMPLE_RATE env var.
_DEFAULT_SAMPLE_RATE = 0.1


def _parse_sample_rate(raw):
    """Parse MEM0_TELEMETRY_SAMPLE_RATE env var. Never raises."""
    try:
        value = float(raw)
    except (TypeError, ValueError):
        _logger.debug("MEM0_TELEMETRY_SAMPLE_RATE %r is not a number, defaulting to %s", raw, _DEFAULT_SAMPLE_RATE)
        return _DEFAULT_SAMPLE_RATE

View on GitHub (pinned to 001c235229)

Solutions

1. Set MEM0_TELEMETRY as a plain string ('true'/'false', '1'/'0', 'yes'/'no'); any other string silently disables telemetry rather than raising
2. If you are patching in tests, patch the module attribute after import, or use string values in os.environ
3. Remove programmatic writes of non-string values into os.environ before importing mem0

Example fix

# before
os.environ["MEM0_TELEMETRY"] = 1  # non-string -> ValueError at import
import mem0

# after
os.environ["MEM0_TELEMETRY"] = "1"  # plain string
import mem0

import os
val = os.environ.get("MEM0_TELEMETRY", "True")
assert isinstance(val, str), "MEM0_TELEMETRY must be a string env value"

When it happens

Trigger: Patching mem0.memory.telemetry.MEM0_TELEMETRY or os.environ['MEM0_TELEMETRY'] with a non-string value (e.g. 1 as int, or a Mock) before importing mem0; test harnesses that inject raw values into os.environ; exotic environments that expose env values as non-strings.

Common situations: Test suites monkeypatching telemetry settings aggressively; CI configurations that inject typed values into the environment; developers surprised that any invalid-looking value like MEM0_TELEMETRY=off does NOT raise (it silently becomes False) while a non-string type does.

Related errors

• Cohere API key is required. Set COHERE_API_KEY environment v
• Zero Entropy API key is required. Set ZERO_ENTROPY_API_KEY e
• PGVector requires either connectionString or ${missingFields
• Pinecone API key required: pass apiKey or set PINECONE_API_K
• Cohere API key is required. Set COHERE_API_KEY environment v

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/e19cc5db174a319c. Report an issue: GitHub.