# Tencent/Metis

Metis is a learnware platform in the field of AIOps.

Repository: https://github.com/Tencent/Metis
Canonical: https://ross.abutalabs.com/products/metis
Language: Python
License: NOASSERTION
License Family: other
Topics: metis, aiops, uweb, python, javascript, typescript, learnware
Archived: true
Last push: 2023-04-07T11:26:43+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2882, "days_push": 1244, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1757, forks 503 (observed 2026-08-28T04:05:32.310650+00:00)

## What it is
Metis is a learnware platform for AIOps from Tencent, currently open-sourcing a time-series anomaly detection learnware. It combines statistical judgment, unsupervised, and supervised learning to detect anomalies in operational metrics, with a web UI and API.

## Use cases
- detect anomalies in time-series server metrics
- build intelligent operations monitoring for large fleets
- train and update supervised anomaly detection models from labeled samples
- replace rule-based ops alerting with machine learning detection
- serve anomaly detection via a web UI or API

## When to choose
- you need ML-based time-series anomaly detection for ops/monitoring metrics
- you run Linux and can work with a Python 2.7 backend
- you want a proven approach validated on millions of production metrics

## When to avoid
- you need modern Python 3 support or active maintenance
- you need large-scale data storage or streaming pipelines, which are out of scope
- you need a general-purpose monitoring platform rather than a detection learnware

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, monitoring, analytics, data-science
- domain: artificial-intelligence, machine-learning, monitoring, time-series
- platform: python
- tags: aiops, learnware, anomaly-detection, time-series, operations, web-ui, devops, linux, web-server

## Member repositories
- Tencent/Metis (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.310650+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:27:38.596903+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/Metis (fetched 2026-08-28T04:05:32.310650+00:00, sha d397ef4f3d8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.