DeadBranches

full-text-tabs-forever

Full text search all your browsing history

reader2

Get a reader mode, sharable URL for any webpage.

ReadabiliPy

A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's Readability.js package or in pure-python mode.

whisper-acft

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

tiny11builder

Scripts to build a trimmed-down Windows 11 image.

logseq-to-org-roam

Scripts to move a Logseq graph to Emacs+Org-Roam

hishtory

Your shell history: synced, queryable, and in context

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

miyagi

Sample to envision intelligent apps with Microsoft's Copilot stack for AI-infused product experiences.

guidance

A guidance language for controlling large language models.

promptbase

All things prompt engineering

cli

🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.

hyperfine

A command-line benchmarking tool

xplr

A hackable, minimal, fast TUI file explorer

thumb-key

A privacy-conscious Android keyboard made for your thumbs

Sayboard

An open-source on-device voice IME (keyboard) for Android using the Vosk library.

openboard

vosk-android-demo

Offline speech recognition for Android with Vosk library.

Sapphire

A free and open source replacement for Google Assistant on Android devices, meant to integrate with the Sapphire Framework. It contains both speech-to-text and text-to-speech services. It does not require Google services or network connectivity

quivr

Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, Groq that you can share with users ! Efficient retrieval augmented generation framework

gptscript

Build AI assistants that interact with your systems

Qwen-Agent

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

fltr

Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.

AutoSmoothQuant

An easy-to-use package for implementing SmoothQuant for LLMs

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

logseq-snippets

Snippets I'm using with logseq.com.

M.I.L.E.S

M.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any Spotify song, adjusts system and Spotify volume, performs calculations, browses the web and internet, searches global weather, delivers date and time, autonomously chooses and retains long-term memories. Available for macOS and Windows.

llama-cpp-agent

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

Medical_Intake

Automated pipeline for medical intake, diagnosis, tests, etc.