Stars
An agentic skills framework & software development methodology that works.
Official, Anthropic-managed directory of high quality Claude Code Plugins.
A collection of formalized statements of conjectures in Lean.
Proof of thought : LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON DSL)
[NeurIPS 2025] Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
LLM Council works together to answer your hardest questions
An alignment auditing agent capable of quickly exploring alignment hypothesis
An incremental parsing system for programming tools
A tool for intelligently chunking and parsing code files, enhancing readability and maintainability by organizing code around key points of interest.
🐍💯pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box.
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
Prompt Engineering at Your Fingertips!
A framework for prompt tuning using Intent-based Prompt Calibration
This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc
Official repo for SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"
RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Improving Alignment and Robustness with Circuit Breakers
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
Bitwuzla is a Satisfiability Modulo Theories (SMT) solver for the theories of fixed-size bit-vectors, floating-point arithmetic, arrays and uninterpreted functions and their combinations. Its name …
Universal and Transferable Attacks on Aligned Language Models
Catch API bugs before your users do
A collection of examples to help users get up and running with Smithy