Sahar

coding-agents-monitor. Tiny macOS widget for monitoring Claude Code and Codex usage

claude-optimize. Scan your Claude-powered app and get a prioritized optimization report to improve performance and reduce latency + cost

EchoScribe. Local AI transcription workspace with cloud APIs (OpenAI Whisper) or local models (Whisper) running entirely on your machine.

litellm-compromised. Check whether a GitHub repository depends on the compromised LiteLLM PyPI releases 1.82.7 or 1.82.8, with remediation guidance if it does

prompt-claude. TypeScript

evernote-trunk. Break free from Evernote. Export all your notes to a beautiful, self-hosted archive you actually own.

wispr-action. Turn your perfectly transcribed speech into real-world actions

tool-use-scheme-generator. Create OpenAI and Anthropic function-calling schemas without writing JSON by hand

auggie-mcp. Run Augment Code as a coding agent via the Auggie CLI

sidekick-dev-web. Automatically generate high-quality markdown context files for AI coding agents like Claude, Cursor, and Gemini, Powered By DeepWiki

ag-ui. AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

cursor-view. Browse, search, export, and share your entire Cursor AI chat history

simulatedev. Run AI coding agents like Cursor, Windsurf, and Claude Code via code and let them implement features all the way to a pull request

schedulesurf. JavaScript

supercode. Enhance your coding experience by letting you interact with your IDE using voice commands. Vibe coding how it should be.

stagehand. The SDK For Browser Agents

gemini-multimodal-playground. Build realtime voice and video agents with Google's new Gemini 2.0 (API is free for now)

ultravox. A fast multimodal LLM for real-time voice

voice-lab-ui. JavaScript

streaming-deep-rl. Explorations into the proposed Streaming Deep Reinforcement Learning, from University of Alberta

voice-lab. Testing and evaluation framework for voice agents

inquiry. Collect user data seamlessly using OpenAI's Realtime API

inquiryold. JavaScript

HebTTS. The official implementation of "A Language Modeling Approach to Diacritic-Free Hebrew TTS"

gateway. A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

wayback-gpt. Python

courses. Anthropic's educational courses

qodo-cover. Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞

hume-gpt. An emotionally intelligent AI powered by GPT-4o

needle-in-a-haystack. Doing simple retrieval from LLM models at various context lengths to measure accuracy

superagent. Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

openllmetry. Open-source observability for your GenAI or LLM application, based on OpenTelemetry

AutoPrompt. A framework for prompt tuning using Intent-based Prompt Calibration

galen-evals. Coworker for Life Sciences

instax-link-web. Vue

gen-ai-monitor. JavaScript

client-python. Python client library for Mistral AI platform

langroid. Harness LLMs with Multi-Agent Programming

One. Surfacing O1/EB1 visa eligible experts.

webcamGPT. webcamGPT - chat with video stream 💬 + 📸

MonsterBooth. Turn yourself into a Halloween-styled character and get an original roast with the power of AI.

Fooocus. Focus on prompting and generating

web-llm. High-performance In-browser LLM Inference Engine

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

gpt-hacks. Jupyter Notebook

keep. The open-source AIOps and alert management platform

optimate. A collection of libraries to optimise AI model performances

CLAP. Contrastive Language-Audio Pretraining

i-Code. Jupyter Notebook

dspy. DSPy: The framework for programming—not prompting—language models

llama_index. LlamaIndex is the leading document agent and OCR platform

gpt-duplex. GPT + Whisper as your assistant for everything bookable via phone

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

point-e. Point cloud diffusion for 3D model synthesis

awesome-chatgpt. Selected ChatGPT demos, tools, articles, and more ✨

anima. Turn text into video using Stable Diffusion and Google FILM

sandbox-toy-semantic-search. A demonstration of how a toy (but usable!) semantic search engine can be quickly built using Cohere's platform.

dust. Custom AI agent platform to speed up your work.

clip-interrogator. Image to prompt with BLIP and CLIP

bleedingedge.ai. Bleeding edge is a feed of noteworthy developments in AI and machine learning.

awesome-whisper. A collection of demos and repositories using OpenAI's Whisper https://openai.com/blog/whisper/

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

whisper-playground. Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

tide. ThisImageDoesnotExist.com

react-gh-pages. Deploying a React App (created using create-react-app) to GitHub Pages

dalle-playground. A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

react-super-cmd. A sleek command palette modal for React apps

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

v-diffusion-jax. v objective diffusion inference code for JAX.

enformer-pytorch. Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

text-generation-testing-ui. Web app for demoing the EAI models

dalle-mini. DALL·E Mini - Generate images from a text prompt

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

gpt-neox. An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them

cleanco. Company Name Processor written in Python

human-eval. Code for the paper "Evaluating Large Language Models Trained on Code"

amazon-transcribe-streaming-sdk. The Amazon Transcribe Streaming SDK is an async Python SDK for converting audio into text via Amazon Transcribe.

realtime-transcription-playground. A real-time transcription project using React and socketio

DALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

alphafold2. To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

python-speech. This library has moved to https://github.com/googleapis/google-cloud-python/tree/main/packages/google-cloud-speech

PICK-pytorch. Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

TokenAware. A Chrome extension to count tokens within OpenAI's GPT-3 Playground

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

fastText. Library for fast text representation and classification.

deep-photo-styletransfer. Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

face_recognition. The world's simplest facial recognition api for Python and the command line

MechanicalSoup. A Python library for automating interaction with websites.

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

tensorflow. An Open Source Machine Learning Framework for Everyone

featexp. Feature exploration for supervised learning

pytext. A natural language modeling framework based on PyTorch

fastai. The fastai deep learning library