vitel
Vitals / interoception for AI agents — graded observability that turns telemetry (metrics, SLOs,
error budgets) into a pass / warn / fail verdict, with every finding grounded in a Metric
(name, window, observed vs threshold, burn-rate).
vitel is a sense organ built on the shared agentsensory
contract — sibling to AgentVision (eyes), Audel (ears) and Verel (brain). Drop it into
CI/CD to gate a release on error-budget burn, or run it as a Verel sense so the brain won't mark a
deploy "done" until post-rollout vitals confirm health.
What it does
| Function | Behavior |
|---|---|
check(source, *, slo=None) |
deterministic threshold / SLO / burn-rate evaluation, no LLM — main path |
analyze(source, *, slo=None, backend=None) |
adds anomaly / LLM critique on top of check |
watch(source, *, window, interval) |
poll / stream over time; trend, degradation, liveness |
render(source) |
normalized series + rates / percentiles / burn-rate (the trustworthy signal) |
Install
pip install vitel # light base: JSON/CSV series + thresholds
pip install "vitel[prometheus]" # PromQL / Prometheus
pip install "vitel[otel]" # OpenTelemetry (OTLP)
pip install "vitel[cloud]" # Datadog / CloudWatch
pip install "vitel[psutil]" # process self-vitals
pip install "vitel[all]" # everything
License
MIT © Amit Patole
1 maintainer
Metadata
1 maintainer
Release files for vitel 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vitel-0.1.0.tar.gz | 161.8 kB | Without provenance | Details for vitel-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vitel-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for vitel-0.1.0-py3-none-any.whl |
Total release size: 211.1 kB
Release files / vitel-0.1.0.tar.gz
| Download URL | vitel-0.1.0.tar.gz |
|---|---|
| Size | 161.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2a0062eccacc2f62f1f9d737a0c71638b63473b0ea21a08c156e4b247740f730
|
|
BLAKE2b-256 checksum How to use checksums |
be1a40d5f4b5195076e7677728f3af181fadca4f06ba48472dcdd70d839b6ec0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Release files / vitel-0.1.0-py3-none-any.whl
| Download URL | vitel-0.1.0-py3-none-any.whl |
|---|---|
| Size | 49.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
abb06510af473cd191c3edc1d70aea634f05a74f8475bd1fd905842b11daedd0
|
|
BLAKE2b-256 checksum How to use checksums |
64c46051a467aae6c1351e882402acd45ddd511322fef17a72862f58f621f1b8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Security for vitel 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
