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. --send-test-event proves the whole pipeline end to end by sending one span event and reporting the ingest response (exit codes: 0 pass, 1 config failure, 2 connectivity failure):

wildedge doctor --integrations all --send-test-event

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	Exit (code 121) if a requested integration can't be instrumented
--strict	Exit (120 config, 122 internal) instead of running untracked when bootstrap fails
--attachments	Enable opt-in raw input/output attachment upload
--no-propagate	Don't pass WildEdge env vars to child processes

SDK

import wildedge

wildedge.init(integrations=["transformers"])  # optional under `wildedge run`

# models loaded after this point are tracked automatically; add traces,
# spans and LLM API calls anywhere, no client instance to pass around:
with wildedge.trace(run_id="run-1"):
    with wildedge.span(kind="agent_step", name="plan"):
        ...

with wildedge.llm_api(model="openai/gpt-4o-mini", provider="openrouter") as call:
    call.response(data)  # LLM calls made with plain HTTP clients

One client per process: wildedge run, init(), and the module-level calls all share it, and init() without dsn reuses whatever already exists. Without a DSN everything is a silent no-op, so dev and CI need no configuration. See Deployment for the full contract.

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
anthropic	anthropic_example.py
openai	openai_example.py

Calling an LLM API with a plain HTTP client instead of these libraries? Use wildedge.llm_api(): llm_api_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). If unset, the client is a no-op.
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)
attachments_enabled	false	Opt-in upload of raw inference inputs/outputs (or WILDEDGE_ATTACHMENTS_ENABLED). See Attachments

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

Projects using this SDK

Name	Link
outfitstudio.app	https://outfitstudio.app/
agntr	github.com/pmaciolek/agntr
demo-app	github.com/wild-edge/demo-app
(your project here)	-

Using WildEdge in your project? Open a PR to add it to the list.

Security & Privacy

By default the SDK transmits only anonymized telemetry, never raw model inputs or outputs. The one exception is opt-in attachments (attachments_enabled), which upload raw bytes you explicitly pass in.

Report security and privacy issues to: support@wildedge.dev

Links

• Deployment guide
• Manual tracking
• LLM API tracking
• Compatibility Matrix
• Changelog
• License

Each GitHub release ships llms.txt and llms-full.txt: the full documentation for that exact version in one file, built for AI assistants.