OpenRunner SDK
Open-source, self-hosted ML experiment tracking — a drop-in replacement for Weights & Biases.
Install
pip install openrunner-sdk
Setup
export OPENRUNNER_API_KEY="or_your_key"
export OPENRUNNER_BASE_URL="https://your-server.com"
Or use the CLI:
openrunner login
Quick Start
import openrunner
# Start a run
openrunner.init(project="my-project", config={"lr": 0.001, "epochs": 10})
# Log metrics in your training loop
for epoch in range(10):
loss = train(epoch)
acc = evaluate()
openrunner.log({"loss": loss, "accuracy": acc, "epoch": epoch})
# End the run
openrunner.finish()
API Reference
Core Functions
openrunner.init()
Initialize a new experiment run.
run = openrunner.init(
project="my-project", # Project name (auto-created if missing)
name="experiment-1", # Optional display name
config={"lr": 0.001}, # Hyperparameters
tags=["baseline", "v2"], # Optional tags
notes="Testing new arch", # Optional notes
group="sweep-1", # Optional group name
job_type="train", # Optional job type
resume=True, # Resume a previous run by ID
)
openrunner.log()
Log metrics. Non-blocking — never slows down training.
# Basic logging
openrunner.log({"loss": 0.5, "accuracy": 0.85})
# With explicit step
openrunner.log({"loss": 0.3}, step=100)
# Log images
openrunner.log({"predictions": openrunner.Image(img_array, caption="epoch 5")})
# Log tables
table = openrunner.Table(
columns=["input", "predicted", "actual"],
data=[["img_01", 7, 7], ["img_02", 3, 5]],
)
openrunner.log({"eval_results": table})
openrunner.finish()
End the current run. Flushes all buffered metrics.
openrunner.finish()
openrunner.finish(exit_code=0) # With exit code
openrunner.finish(quiet=True) # Suppress output
Config
Dict-like object with dot notation. Set at init(), accessible throughout the run.
openrunner.init(config={"optimizer": {"lr": 0.001, "weight_decay": 1e-5}})
# Access
print(openrunner.config["optimizer.lr"]) # 0.001 (flattened keys)
print(openrunner.config.optimizer.lr) # 0.001 (dot notation)
# Update after init
openrunner.config.update({"batch_size": 64})
openrunner.config["new_param"] = "value"
Summary
Auto-updated with the last logged value for each key. Can also be set explicitly.
# Auto-populated from log()
openrunner.log({"loss": 0.5})
openrunner.log({"loss": 0.3})
print(openrunner.summary["loss"]) # 0.3 (last value)
# Explicit set
openrunner.summary["best_accuracy"] = 0.95
openrunner.summary["final_loss"] = 0.1
Artifacts
Version datasets, models, and checkpoints with content-hash deduplication.
# Log a model artifact
artifact = openrunner.Artifact(name="my-model", type="model")
artifact.add_file("model.pth")
artifact.add_file("config.json")
run.log_artifact(artifact)
# Use an artifact from a previous run
artifact = run.use_artifact("my-model:v2")
artifact.download("/path/to/dir")
Media Types
Images
import numpy as np
# From numpy array
img = openrunner.Image(np.random.rand(28, 28, 3), caption="sample")
# From PIL Image
from PIL import Image as PILImage
pil_img = PILImage.open("photo.png")
img = openrunner.Image(pil_img, caption="photo")
# From file path
img = openrunner.Image("output.png", caption="result")
openrunner.log({"examples": img})
Tables
table = openrunner.Table(
columns=["epoch", "loss", "accuracy"],
data=[
[1, 0.9, 0.65],
[2, 0.5, 0.82],
[3, 0.3, 0.91],
],
)
openrunner.log({"metrics_table": table})
Run Properties
run = openrunner.init(project="test")
print(run.id) # "a1b2c3d4" (8-char ID)
print(run.name) # Display name
print(run.project) # Project name
print(run.config) # Config object
print(run.summary) # Summary object
HTML
# Log raw HTML for rich reports, custom visualizations, or formatted output
openrunner.log({"report": openrunner.Html("<h1>Training Report</h1><p>Loss converged at epoch 42.</p>")})
Histograms
import numpy as np
weights = np.random.randn(10000)
openrunner.log({"weight_dist": openrunner.Histogram(weights, num_bins=50)})
Plotly Charts
import plotly.graph_objects as go
fig = go.Figure(data=go.Scatter(x=[1, 2, 3], y=[4, 5, 6]))
openrunner.log({"interactive_plot": openrunner.Plotly(fig)})
Point Clouds
import numpy as np
points = np.random.randn(1000, 3)
colors = np.random.randint(0, 255, (1000, 3), dtype=np.uint8)
openrunner.log({"lidar": openrunner.PointCloud3D(points, colors=colors)})
Bounding Boxes
img = openrunner.Image("photo.jpg")
boxes = [{"position": {"minX": 10, "minY": 20, "maxX": 100, "maxY": 150}, "class_id": 0}]
openrunner.log({"detections": openrunner.BoundingBoxes2D(img, boxes, class_labels={0: "cat"})})
Audio
import numpy as np
# From numpy array (mono, float32, -1 to 1)
audio = openrunner.Audio(np.random.randn(44100).astype(np.float32), sample_rate=44100)
openrunner.log({"audio_sample": audio})
Video
# From file path
openrunner.log({"demo": openrunner.Video("output.mp4", caption="training demo")})
Matplotlib Figures
import matplotlib.pyplot as plt
plt.figure()
plt.plot([1, 2, 3], [4, 5, 6])
openrunner.log({"chart": openrunner.MatplotlibFigure()}) # captures current figure
plt.close()
LLM Tracing
Trace LLM API calls for debugging and cost tracking.
import openrunner
openrunner.init(project="llm-app")
# Auto-trace OpenAI calls
openrunner.trace.patch_openai()
# Or manually trace any function
@openrunner.trace
def generate(prompt):
return client.chat.completions.create(
model="gpt-4", messages=[{"role": "user", "content": prompt}]
)
Hyperparameter Sweeps
Run distributed hyperparameter searches.
import openrunner
sweep_config = {
"method": "bayes",
"metric": {"name": "val_loss", "goal": "minimize"},
"parameters": {
"lr": {"min": 1e-5, "max": 1e-2, "distribution": "log_uniform"},
"epochs": {"values": [10, 20, 50]},
},
}
sweep_id = openrunner.sweep(sweep_config, project="my-project")
def train():
run = openrunner.init()
lr = openrunner.config.lr
# ... training loop ...
openrunner.finish()
openrunner.agent(sweep_id, function=train, count=20)
Remote Launch
Submit training jobs to remote infrastructure.
import openrunner
job = openrunner.launch(
project="my-project",
config={"lr": 0.001, "epochs": 50},
resource="gpu-a100",
)
job.wait() # block until finished
print(job.state) # "finished"
Model Registry
Version and alias models for production deployment.
# Log a model with aliases
artifact = openrunner.Artifact(name="classifier", type="model")
artifact.add_file("model.pt")
openrunner.link_artifact(artifact, aliases=["staging"])
# Use a model by alias
model_dir = openrunner.use_artifact("classifier:production")
Alerts
Send notifications when training reaches milestones or encounters issues.
openrunner.alert(title="Training complete", text="Final accuracy: 95.2%", level="INFO")
openrunner.alert(title="Loss spike detected", level="WARN")
Query API
Read-only access to runs, metrics, and projects for analysis and dashboards.
api = openrunner.Api()
runs = api.runs("my-project", filters={"state": "finished"})
for run in runs:
print(f"{run.name}: {run.summary.get('accuracy')}")
Migrating from W&B
Change one import — everything else stays the same:
# Before
import wandb
wandb.init(project="my-project")
wandb.log({"loss": 0.5})
wandb.finish()
# After
import openrunner as wandb
wandb.init(project="my-project")
wandb.log({"loss": 0.5})
wandb.finish()
Framework Integrations
PyTorch
from openrunner.integration.pytorch import log_gradients
openrunner.init(project="pytorch-example")
for batch in dataloader:
loss = model(batch)
loss.backward()
log_gradients(model) # Logs gradient norms
optimizer.step()
openrunner.finish()
HuggingFace Transformers
from openrunner.integration.huggingface import OpenRunnerCallback
openrunner.init(project="hf-example")
trainer = Trainer(
model=model,
args=training_args,
callbacks=[OpenRunnerCallback()],
)
trainer.train()
openrunner.finish()
PyTorch Lightning
from openrunner.integration.lightning import OpenRunnerLogger
logger = OpenRunnerLogger(project="lightning-example")
trainer = pl.Trainer(logger=logger)
trainer.fit(model)
Keras
from openrunner.integration.keras import OpenRunnerCallback
openrunner.init(project="keras-example")
model.fit(x_train, y_train, callbacks=[OpenRunnerCallback()])
openrunner.finish()
XGBoost
from openrunner.integration.xgboost import OpenRunnerCallback
openrunner.init(project="xgboost-example")
bst = xgb.train(params, dtrain, callbacks=[OpenRunnerCallback()])
openrunner.finish()
scikit-learn
from openrunner.integration.sklearn import log_model
openrunner.init(project="sklearn-example")
model.fit(X_train, y_train)
log_model(model) # Logs parameters and metrics
openrunner.finish()
FastAI
from openrunner.integration.fastai import OpenRunnerCallback
openrunner.init(project="fastai-example")
learn = cnn_learner(dls, resnet34, cbs=[OpenRunnerCallback()])
learn.fine_tune(5)
openrunner.finish()
LangChain
from openrunner.integration.langchain import OpenRunnerTracer
openrunner.init(project="langchain-example")
tracer = OpenRunnerTracer()
chain.invoke({"input": "Hello"}, config={"callbacks": [tracer]})
openrunner.finish()
Offline Mode
Train without connectivity, sync later:
export OPENRUNNER_MODE=offline
python train.py
# When back online
openrunner sync
Offline runs are stored as JSONL files (human-readable, crash-safe). Sync is additive and idempotent — interrupted syncs resume without data loss.
CLI
# Authenticate
openrunner login
# Sync offline runs
openrunner sync
# List projects and runs
openrunner ls
System Metrics
Automatically collected during training (enabled by default):
- CPU utilization (%)
- System memory usage (%)
- GPU utilization (%) — requires
pip install openrunner-sdk[gpu] - GPU memory usage (%)
Disable with:
export OPENRUNNER_SYSTEM_METRICS=false
Environment Variables
| Variable | Description | Default |
|---|---|---|
OPENRUNNER_API_KEY |
API key for authentication | (required) |
OPENRUNNER_BASE_URL |
Server URL | http://localhost:8000 |
OPENRUNNER_PROJECT |
Default project name | (none) |
OPENRUNNER_MODE |
online or offline |
online |
OPENRUNNER_SYSTEM_METRICS |
Enable system metrics | true |
OPENRUNNER_OFFLINE_DIR |
Offline storage directory | ~/.openrunner/offline |
W&B env vars (WANDB_API_KEY, WANDB_BASE_URL) are also supported as fallback for migration.
Self-Hosting
OpenRunner is designed to be self-hosted. See the main repo for server setup with Docker Compose.
License
MIT
2 maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
openrunner_sdk-2.37.21.tar.gz
(511.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file openrunner_sdk-2.37.21.tar.gz.
File metadata
- Download URL: openrunner_sdk-2.37.21.tar.gz
- Upload date:
- Size: 511.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
96a1a75523b1f18e4f4d38b9d37c3cd82d28b5fe62f267b53aae102b6d359cf1
|
|
| MD5 |
64a0bea471a41a0ee1034f6007e28bc2
|
|
| BLAKE2b-256 |
39313fe9948fa6f360a13df305954afa014e31cad869cdafa41629b0e5a35b0d
|
File details
Details for the file openrunner_sdk-2.37.21-py3-none-any.whl.
File metadata
- Download URL: openrunner_sdk-2.37.21-py3-none-any.whl
- Upload date:
- Size: 465.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6ba84ee90dd80456d33b6e8a6df839f4b952f3d0939620f979c1fb3685ae77a7
|
|
| MD5 |
62589880e203138c8fd1d71560b2e4b9
|
|
| BLAKE2b-256 |
70cd10ab2f719cb521583104dc878b548e5317260f08ef0d43a90be7bc738e02
|
