# numenta/nupic-legacy

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

Repository: https://github.com/numenta/nupic-legacy
Canonical: https://ross.abutalabs.com/products/nupic-legacy
Homepage: http://numenta.org/
Language: Python
License: MIT
License Family: permissive
Topics: neocortex, artificial-intelligence, machine-intelligence, hierarchical-temporal-memory
Last push: 2024-12-03T17:50:20+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4898, "days_push": 638, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6350, forks 1529 (observed 2026-08-28T04:09:42.749007+00:00)

## What it is
NuPIC is Numenta's open-source machine intelligence platform implementing Hierarchical Temporal Memory (HTM), a computational theory of the neocortex with time-based continuous learning algorithms. This legacy repository is in maintenance mode, receiving only critical bug fixes and research-supporting changes.

## Use cases
- detect anomalies in streaming sensor data
- predict future values in continuous time-series streams
- experiment with neuroscience-based learning algorithms
- implement HTM spatial and temporal pattern memory
- research brain-inspired machine intelligence models
- build online learning systems without labeled training data

## When to choose
- you want to study or extend HTM/neocortical learning algorithms
- you need streaming anomaly detection with continuous online learning
- you're doing research on biologically plausible intelligence models

## When to avoid
- you need a modern, actively developed ML framework
- you require Python 3 or current OS support (it targets Python 2.7 and old platforms)
- you want production-grade deep learning or LLM capabilities
- you need community-driven feature development

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, streaming, analytics
- domain: machine-learning, artificial-intelligence, time-series
- platform: python, windows, cross-platform
- tags: htm, neocortex, neuroscience-inspired-ai, anomaly-detection, temporal-pattern-learning, legacy, algorithms, linux, macos

## Member repositories
- numenta/nupic-legacy (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:42.749007+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 2026-08-29T17:46:06.773984+00:00, confidence not recorded.
  - readme: https://github.com/numenta/nupic-legacy (fetched 2026-08-28T04:09:42.749007+00:00, sha 6bed42977342)
  - homepage: http://numenta.org/ (fetched 2026-08-29T08:42:33.896981+00:00, sha 60a8f7fff91c)
  - site_page: https://www.numenta.com/company (fetched 2026-08-29T08:42:33.899401+00:00, sha 704c73356ba5)
- Data as of 2026-08-30T08:39:29.467469+00:00.