wildedge-sdk 0.1.1

On-device ML inference monitoring for Python

WildEdge Python SDK

On-device ML inference monitoring for Python. Tracks latency, errors, and model metadata without any code modifications.

Pre-release: The API is unstable and may change between versions. Semantic versioning will apply from the first stable release.

Install

uv add wildedge-sdk

CLI

Drop wildedge run in front of your existing command. WildEdge instruments the runtime before your code starts. No SDK calls required in user code.

WILDEDGE_DSN="https://<secret>@ingest.wildedge.dev/<key>" \
wildedge run --integrations timm -- python app.py

Validate your environment before deploying:

wildedge doctor --integrations all --network-check

Useful flags:

Flag	Description
--integrations	Comma-separated list of integrations to activate (or all)
--hubs	Hub trackers to activate: huggingface, torchhub
--print-startup-report	Print per-integration status at startup
--strict-integrations	Fail if a requested integration can't be loaded
--no-propagate	Don't pass WildEdge env vars to child processes

SDK

import wildedge

client = wildedge.WildEdge(dsn="...")  # or WILDEDGE_DSN env var
client.instrument("transformers", hubs=["huggingface"])

# models loaded after this point are tracked automatically

Supported integrations

On-device

Integration	Example
transformers	transformers_example.py
mlx	mlx_example.py
timm	timm_example.py
gguf	gguf_example.py
onnx	onnx_example.py
ultralytics	-
tensorflow	tensorflow_example.py
torch	pytorch_example.py
keras	keras_example.py

Remote models

Integration	Example
openai	openai_example.py

Hub tracking

Pass hubs= to track model download provenance. Hubs are framework-agnostic and can be combined with any integration.

Hub	Tracks
huggingface	Downloads via huggingface_hub
torchhub	Downloads via torch.hub

For unsupported frameworks, see Manual tracking.

Configuration

Parameter	Default	Description
dsn	-	https://<secret>@ingest.wildedge.dev/<key> (or WILDEDGE_DSN)
app_version	None	Your app's version string
app_identity	<project_key>	Namespace for offline persistence. Set per-app in multi-process workloads (or WILDEDGE_APP_IDENTITY)
enable_offline_persistence	true	Persist unsent events to disk and replay on restart
sampling_interval_s	30.0	Seconds between background hardware snapshots. Set to 0 or None to disable (or WILDEDGE_SAMPLING_INTERVAL_S)

For advanced options (batching, queue tuning, dead-letter storage), see Configuration.

Privacy

Report security & priact issues to: [e-mail].

Links

• Compatibility Matrix
• Changelog
• License