# undertheseanlp/underthesea

Underthesea - AI Assistant

Repository: https://github.com/undertheseanlp/underthesea
Canonical: https://ross.abutalabs.com/products/underthesea
Homepage: http://undertheseanlp.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: nlp, vietnamese, word-segmenter, agents, llm, agentic-ai, ai, assistant, hermes-agent, openclaw
Last push: 2026-08-26T05:18:54+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 3472, "days_push": 7, "days_rel": 108, "gap_med": 0.0, "n_releases_24m": 25}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1804, forks 309 (observed 2026-08-28T04:05:38.825772+00:00)

## What it is
Underthesea is an open-source Python toolkit for Vietnamese natural language processing that has evolved into an agentic AI toolkit with multi-provider LLM agent support (OpenAI, Azure OpenAI, Anthropic, Gemini) using zero external dependencies. It combines Vietnamese NLP modules like word segmentation with a lightweight Agent framework built on Python stdlib.

## Use cases
- segment Vietnamese text into words
- build an AI agent that talks to OpenAI or Claude without extra dependencies
- do Vietnamese NLP in Python
- switch between multiple LLM providers with one interface
- process Vietnamese text for chatbots
- run Vietnamese NLP in a Colab notebook

## When to choose
- you need Vietnamese-specific NLP like word segmentation
- you want a dependency-free agent that calls LLM APIs with stdlib only
- you need multi-provider LLM support (OpenAI, Anthropic, Gemini, Azure)
- you want a mature, well-maintained Vietnamese NLP library

## When to avoid
- you need NLP for languages other than Vietnamese
- you need a full-featured agent framework with tools, memory, and orchestration
- you need high-performance production LLM features like streaming or retries

## Facets
- artifact type: library
- maturity: active
- function: nlp, agent-framework, llm-inference, machine-learning, sdk
- domain: artificial-intelligence, large-language-models, machine-learning
- platform: python, cross-platform
- tags: vietnamese, word-segmentation, multi-provider-llm, zero-dependency-agent, open-source, natural-language-processing, ai-agents

## Member repositories
- undertheseanlp/underthesea (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:38.825772+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 2026-08-30T03:21:50.684367+00:00, confidence not recorded.
  - readme: https://github.com/undertheseanlp/underthesea (fetched 2026-08-28T04:05:38.825772+00:00, sha bb70696e7360)
  - homepage: http://undertheseanlp.com (fetched 2026-08-29T11:00:48.309018+00:00, sha 1690f4eee6df)
  - registry_pypi: https://pypi.org/pypi/underthesea/json (fetched 2026-08-29T11:00:48.318463+00:00, sha e7b639cc399d)
- Data as of 2026-08-30T08:39:29.467469+00:00.