Letta (formerly MemGPT) is a framework for creating LLM services with memory.

A self hosted virtual browser that runs in docker and uses WebRTC.

收藏的一些经典的历史、政治、心理、哲学、数学、计算机方面电子书(约10万本）

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

Blazing fast concurrent HashMap for Rust.

SeBS: serverless benchmarking suite for automatic performance analysis of FaaS platforms.

A library for building fast, reliable and evolvable network services.

Snappy compression implemented in Rust (including the Snappy frame format).

The Rust Implementation of the libp2p networking stack.

Python library for handling efficiently sorted integer sets.

A Go implementation of STUN

Fast TURN and STUN server: cross-platform, hot reload, flexible config

Fast RFC 5389 STUN implementation in go

Lightweight STUN/TURN server

End-to-End Speech Processing Toolkit

A Docker Container to easily run a Palworld dedicated server.

🐚 An async & dynamic ORM for Rust

Zero-copy deserialization framework for Rust

A benchmark suite for serverless computing

KvikIO - High Performance File IO

Chinese software copyright application template document

Implementation of the Lox language in Langium

FlatBuffers: Memory Efficient Serialization Library

Benchmarks for rust serialization frameworks

VSCode extension for Unreal and clangd

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…

TypeChat is a library that makes it easy to build natural language interfaces using types.

ShaderNN is a lightweight deep learning inference framework optimized for Convolutional Neural Networks on mobile platforms.