#nlp

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

Keine Repository-Beschreibung veröffentlicht.

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

Python package for the NLP Engine

🔮 A refreshing functional take on deep learning, compatible with your favorite libraries

Reads dates written by humans in 40 languages, and reckons across 17 calendar systems — answers are spans, not instants, from deep time to next Tuesday. Refuses to guess when history cannot know.

FastroAI wraps PydanticAI with production essentials: cost tracking in microcents, multi-step pipelines, and tools that handle failures gracefully.

31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.

초경량 한국어 형태소 분석기 — 1MB 모델로 브라우저에서 실행(WASM). Ultra-lightweight Korean morphological analyzer in the browser. npm: garu-ko

Keine Repository-Beschreibung veröffentlicht.

NLP engine code

Let your users ask your database anything, in their own words — safely. The model fills in a validated Query AST, never a query string, and deterministic Go compiles it to SQL, MongoDB or whatever backend you add. Config-driven, read-only by design, standard-library Go.

A consistent, fair, benchmark for structured extraction.

Pure JS fast phonemizer with rule-based G2P prediction

A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.

Taiwan Traditional Chinese quality tool for AI-generated content (CLI + 6-language SDK, 31K terms / 100M-char zero-mistranslation validation)

Graph memory for AI agents: facts in, entities and cause->effect relations extracted with small open models, multi-hop recall with a cited chain. Library, HTTP/MCP service, LangChain, hosted at memory.primaxiom.ai

Python library for the Caplena REST API.

Heuristic code and docs metrics for spotting AI slop, overengineering, and filler at a glance.