Adding guardrails to large language models.

A system for quickly generating training data with weak supervision

Reverse engineering and pentesting for Android applications

Rules engine for cloud security, cost optimization, and governance, DSL in yaml for policies to query, filter, and take actions on resources

Windows GUI Automation with Python (based on text properties)

A True Instrumentable Binary Emulation Framework

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

The FLARE team's open-source tool to identify capabilities in executable files.

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

🌊 Online machine learning in Python

CloudEvents Specification

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and…

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

GRR Rapid Response: remote live forensics for incident response

The x86 processor fuzzer

🐢 Open-Source Evaluation & Testing library for LLM Agents

The AWS exploitation framework, designed for testing the security of Amazon Web Services environments.

A fast and reliable background task processing library for Python 3.

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Tool for partial deblobbing of Intel ME/TXE firmware images

Responder is a LLMNR, NBT-NS and MDNS poisoner, with built-in HTTP/SMB/MSSQL/FTP/LDAP rogue authentication server supporting NTLMv1/NTLMv2/LMv2, Extended Security NTLMSSP and Basic HTTP authenticat…

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

A tool that automatically formats Python code to conform to the PEP 8 style guide.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

A community-driven, open-source project to share detection logic, adversary tradecraft and resources to make detection development more efficient.

A fast inference library for running LLMs locally on modern consumer-class GPUs

IntelOwl: manage your Threat Intelligence at scale