GPT4All: Chat with Local LLMs on Any Device

LLM inference in C/C++

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

A library for efficient similarity search and clustering of dense vectors.

Distribute and run LLMs with a single file.

Cap'n Proto serialization/RPC system - core tools and C++ library

Unsupervised text tokenizer for Neural Network-based text generation.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Header-only C++/python library for fast approximate nearest neighbors

Triton is a dynamic binary analysis library. Build your own program analysis tools, automate your reverse engineering, perform software verification or just emulate code.

Fast inference engine for Transformer models

KenLM: Faster and Smaller Language Model Queries

Host for Moonlight Streaming Client

Linux port of FAR v2

Disable PatchGuard and Driver Signature Enforcement at boot time

Virtual-machine Translation Intermediate Language

revng: the core repository of the rev.ng project

Library for lifting machine code to LLVM bitcode

A Pin Tool for tracing API calls etc

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

Soufflé is a variant of Datalog for tool designers crafting analyses in Horn clauses. Soufflé synthesizes a native parallel C++ program from a logic specification.

LLMs as Copilots for Theorem Proving in Lean

SymCC: efficient compiler-based symbolic execution

RetDec plugin for IDA

Practical mutation testing and fault injection for C and C++

Hex-Rays microcode API plugin for breaking an obfuscating compiler

An optimizing decompiler

A fast and accurate disassembler