Answer.AI ORG

The fastest way to create an HTML app

Create delightful software with Jupyter Notebooks

A lightweight library for portable low-level GPU computation using WebGPU.

The /llms.txt file, helping language models use your website

Bringing BERT into modernity via both architecture changes and scaling

Python supercharged for the fastai library

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Training LLMs with QLoRA + FSDP

Simple and flexible progress bar for Jupyter Notebook and console

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

Example fasthtml applications demonstrating a range of web programming techniques

A delightful and complete interface to GitHub's amazing API

MonsterUI is a FastHTML Tailwind-powered UI framework for building beautiful web interfaces with minimal code.

Setup all the things

ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly

Claudette is Claude's friend

A bit of extra usability for sqlite

Convert clipboard from HTML to MD

No description.

Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.

Execute a jupyter notebook, fast, without needing jupyter

No description.

No description.

No description.

Convert a web page to markdown

No description.

Get a markdown version of any webpage with a keyboard shortcut.

Tools to make language models a bit easier to use

Send email using markdown

A Jupyter kernel for Mojo

No description.

No description.

Claudette's sister, a helper for OpenAI GPT

Example dialogs to get your creative juices flowing

Fastest way to use the Stripe API in python

Composite Actions workflows for use in fastai projects

A miniture AI training framework for PyTorch

Deployment examples for FastHTML

A FastHTML wrapper for Daisy-UI

litellm helper

No description.

Simple database migrations for SQLite

Huggingface deployment for FastHTML

Transform is the main building block of data pipelines in fastai. And elsewhere if you want.

Useful LLM contexts ready to be used in AIMagic

Run python scripts, auto-installing their dependencies in cached, isolated environments

about.fastht.ml source

fasthtml wrapper for bootstrap

A terminal IPython extension that adds Claude and Codex powered prompting

A simple python wrapper for using the Caddy API

Helper functions for solveit dialogs

Cache your API calls with a single line of code. No mocks, no fixtures. Just faster, cleaner code.

Python tools for Anki

nbdev docs lookup for a few libraries and python itself

Convenient access to `pynvml` (the library behind `nvidia-smi`)

Create an LLM XML context document from an llms.txt file

Code to go with beginner FastHTML tutorial

No description.

No description.

Use sync mode Playwright interactively, inside a Jupyter notebook

A simple uv workspace

A fork of sqlite-utils with CLI etc removed

Paste Word, get Markdown

Call commands safely by checking them rigorously against an allow-list

msglm makes it a little easier to create messages for language models like Claude and OpenAI GPTs.

Gmail / Google Workspace email client built on the Gmail API

No description.

No description.

Style checker for fast.ai coding conventions

Wrapper for Gemini's API

Python-native skills system

An IPython magic for persistent bash

Safe(ish) running of python code

A lightweight execution guard for running LLM-generated Python in a normal Python process

Automatically create backups of a directory

The easiest way to create your blog on solveit!

fontawesome 6 free icons as SVGs

A high-throughput and memory-efficient inference and serving engine for LLMs

Python API for ripgrep-style walking and search

No description.

No description.

Lucide icons for FastHTML

Generate manifest of public symbols win python projects w/docstrings

A data structure that allows you to insert a new item between any two existing items, or at the start or end

No description.

Typography styles for Tailwind CSS v4. A CSS-native alternative to @tailwindcss/typography.

Use git from python, fast

Claude Code plugins from Answer.AI

Local-first release CLI tools: ship_bump, ship_pypi, ship_release_gh

Experimental mini python jupyter kernel

Chrome extension that bridges Solveit's Python backend with your browser

IPython extension for backtick-triggered AI prompts.

Javascript for FastHTML apps

Turn notebooks into LLM-useable text/XML

Experimental minimalist API for redis

Sample FastHTML vercel app

Extract function and method signatures from source code across multiple languages.

Extended markdown features for mistletoe, including subscript, superscript, highlighting, emojis, footnotes, task lists, and more.

Verified Line-Addressed File Editor

Using pyinstrument to profile FastHTML apps

Fast workspace tools for multi-repo management

An nbextension that adds codefolding functionality from CodeMirror to a codecell

Tiny, CDN-friendly helpers to make jQuery traversal and ergonomics snappier

Publish notebooks as Github gists with a single button click

No description.

Dynamic OpenAPI and discovery spec client for Python — turn any API spec into a fully-typed async client with attribute chaining, streaming, and file uploads

Codex plugins and skills from Answer.AI

Complete access to the Cloudflare SDK

Lightweight Chrome Debug Protocol (CDP) client for python

AST-level execution tracing via sys.monitoring

A simple wrapper for asyncpg

A sqlite router for caddy

No description.

A fork of sqlite-minutils for apsw

No description.

Launch Google Chrome with CDP remote debugging enabled

Public repo for HF blog posts

Experiments using Efficient AttentionCLA, MH Latent Attention, GIST, Local-Global, Landmark Attention, YOCO)

Discord user installable app to share a message by DM to self

Access to current notebook and cell in an nbclassic notebook

Experimental q[X]ora kernel development code

Run background terminal sessions by driving `tmux`

Launches commands under in a macOS or Linux sandbox and only allows writes beneath the directory where it was started

No description.

A tiny asyncio-first runtime helper library for services that own event loops, sockets, background threads, and request/reply waiters.

Small pure-Python package that renders a PNG with kitty's graphics protocol using Unicode placeholders

Vite plugin for FastHTML/MonsterUI that automates installation & building

No description.

Allows notebook to have collapsible sections, separated by headings

No description.

Small Python client for Model Context Protocol (MCP) servers.

Like ipyai, but with a codex app server backend

An IPython magic for Dyalog APL

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Official implementation of Half-Quadratic Quantization (HQQ)

drawing problem solving game

No description.

Markdown to XHTML convertor

A tiny stdlib-only package for waiting until a process exits

A modern, lightweight syntax highlighter for python

Compile a small Python-shaped DSL into Apple Shortcuts on macOS.

No description.

ipython extended for markdown and images, with more complete output history

Lightweight Chrome Debug Protocol (CDP) client for solveit

No description.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Simplified opinionated cloud init for ubuntu

A lightweight way to run an interactive terminal session in the background from Python

A lightweight local Linux dev environment using Docker -- a simple alternative to WSL for macOS

Workspace for ipymini

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

nbz is a typer-based wrapper around the incredible nbdev project.

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

Vim plugin for LLM-assisted code/text completion

Access large language models from the command-line

A helper library for accessing Google Vertex AI models

Public files repo

No description.

Makes notebook markdown attached images display as retina (2x) images

🗿 Mini jQuery alternative. Dependency-free animations. Locality of Behavior. Use one element or arrays transparently. Pairs with htmx. Vanilla querySelector() but better!

🌘 Scope your inline style tags in pure vanilla CSS! Only 16 lines. No build. No dependencies.

8-bit CUDA functions for PyTorch

A tiny notebook experiment

A tiny stdin/stdout worker that keeps a Python process alive and returns concise text for each request

Concurrent-safe Jupyter KernelClient

Automate GitHub social preview image updates from your repository README

Black formatter extension for nbdev export

Template for nbdev 3

Like jupyter_client, but for websockets

A pure Vim9 plugin for Vim on macOS/Linux that talks to `codex app-server`

Build jai

analysis of impact of ai on pypi ecosystem

No description.

No description.

Minimal ipykernel subclass that removes a troublesome lock

IPython Kernel for Jupyter

A fun mini shellsage clone

Simple and fast low-bit matmul kernels in CUDA / Triton

_hyperscript ⋅ Vim / Neovim syntax files

Storing long contexts in tiny caches with self-study

Fast and memory-efficient exact attention

VS Code extension for LLM-assisted code/text completion

No description.

Testing Devin To See If It Can Analyze Anthropic Caching Pricing

No description.

Collect all running headers and display them in a floating window, as a sidebar or with a navigation menu

Implementation of vocoders empowered with pytorch lightning

Unofficial implementation of miipher

LLM training in simple, raw C/CUDA

SGLang is a fast serving framework for large language models and vision language models.

No description.

No description.

No description.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

A high-throughput and memory-efficient inference and serving engine for LLMs

No description.

No description.

Extension library to fasthtml that makes it very simple to create custom context menus