Fixing bugs and reissuing Benoit, Munger & Spirling software

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Database format for Australian Federal Parliament Hansard

An Open Source implementation of Notebook LM with more flexibility and features

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

Train word and document vectors using quanteda

Generate Python Package with Simple Prompts

A playbook for effectively prompting post-trained LLMs

the simplest self-building coding agent

Empowering RAG with a memory-based data interface for all-purpose applications!

SOTA Open Source TTS

Structured information extraction from documents

Chat with any codebase in under two minutes | Fully local or via third-party APIs

[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

OpenResearcher, an advanced Scientific Research Assistant

Positron, a next-generation data science IDE

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A nanoGPT pipeline packed in a spreadsheet

llama3 implementation one matrix multiplication at a time

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Build AI assistants that interact with your systems

Distributed Representations of Words using word2vec

Build ChatGPT over your data, all with natural language

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

flairR: Bring Amazing Flair NLP to R

A social networking service scraper in Python