pelikhan

quality-prompts

TaskTracker

TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a simple linear probe-based method and a more sophisticated metric learning method to achieve this. The project also releases the computationally expensive activation data to stimulate further AI safety research.

tsx

⚡️ TypeScript Execute | The easiest way to run TypeScript in Node.js

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs)

twoslash

Markup for generating rich type information in your documentations ahead of time.

Agentless

Agentless🐱: an agentless approach to automatically solve software development problems

prompt-api

A proposal for a web API for prompting browser-provided language models

maestro

A framework for Claude Opus to intelligently orchestrate subagents.

graphrag-accelerator

One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure

TOXIGEN

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.

vscode-pull-request-github

GitHub Pull Requests for Visual Studio Code

picopilot

GitHub Copilot in 70 lines of JavaScript

mistral.rs

Blazingly fast LLM inference.

pint-benchmark

A benchmark for prompt injection detection systems.

do-not-answer

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

language-models-on-the-command-line

Handout for a talk I gave about LLM and CLI tools

moatless-tools

We Have No Moat, And Neither Does Devin

transformers.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

augmentoolkit

Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!

llama-fs

A self-organizing file system with llama 3

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

astro

The web framework for content-driven websites. ⭐️ Star to support our work!

vscode

VS Code extension for Vitest

BIPIA

A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.

prompt-injection-mitigations

A collection of prompt injection mitigation techniques.

HouYi

The automated prompt injection framework for LLM-integrated applications.

Open-Prompt-Injection

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

rebuff

LLM Prompt Injection Detector