# wit-ai/pywit

Python library for Wit.ai

Repository: https://github.com/wit-ai/pywit
Canonical: https://ross.abutalabs.com/products/pywit
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-08-19T00:50:19+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 4356, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1485, forks 354 (observed 2026-08-28T04:04:51.466572+00:00)

## What it is
pywit is the official Python SDK for Wit.ai, Facebook's natural language processing platform. It provides a Wit client class for extracting intents and entities from text and audio via the Wit.ai HTTP API.

## Use cases
- extract intents and entities from user text with wit.ai
- send a wav audio file to wit.ai speech api for transcription
- build a python chatbot that understands natural language commands
- run an interactive command-line conversation with a wit.ai bot
- parse 'set an alarm tomorrow at 7am' style commands in python

## When to choose
- you already use Wit.ai and need a Python client
- you want a thin, simple wrapper over the Wit.ai HTTP API
- you need both text (message) and audio (speech) NLU in one SDK

## When to avoid
- you want a self-hosted NLU solution without a cloud dependency
- you need a framework for building full conversational agents rather than an API client
- you prefer on-device or offline speech recognition

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, speech-recognition, sdk, http-client
- domain: speech-processing, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: wit-ai, intent-recognition, chatbot-sdk, api-client, natural-language-processing

## Member repositories
- wit-ai/pywit (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.466572+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 2026-08-30T04:33:57.866451+00:00, confidence not recorded.
  - readme: https://github.com/wit-ai/pywit (fetched 2026-08-28T04:04:51.466572+00:00, sha 877ec1b3c21a)
- Data as of 2026-08-30T08:39:29.467469+00:00.