WeWorkBuddy

首页 / 浏览

开源项目与工具

了解开源项目的用途、运行门槛、集成方式与采用证据。

817 条公开内容

Hacker News ·

Show HN: Open-Source DaiDocs now beats Graphify by 218x low tokens, 83% on LME

We have been working on making an Open-Source standard documents for AI LLM's and Agents. Just like an excel file, .dai (Document AI) is a new standard to keep memory local and use with any AI agents and LLM's. This new standard comes with lots of features such as more than 10x tokens savings (tested on LongMemEval-S) when comapred the .dai to raw files and scored 83% with gpt-4-0 and 92% with Fable 5! (This shows how well it remembers a very long conversation), as well as an increased context w

Hacker News ·

Show HN: I remade Mortyr's 2093-1944 engine using my own programming language

Hello, HN! Today I want to show my recent project called PanzerMortyr . It's a reimplementation of the engine of the game Mortyr 2093-1944 ( https://en.wikipedia.org/wiki/Mortyr ). The most interesting thing about it is that it's written in my own programming language named Ü, which I developed previously and continue developing. See https://news.ycombinator.com/item?id=45769161 , https://github.com/Panzerschrek/U-00DC-Sprache/ . I have spend almost a year developing PanzerMortyr . It took a lot

Hacker News ·

Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents

Hey HN, Anders and Tom here. We're building Magnitude, an inference engine for agents that optimizes itself to run as fast as possible on your hardware. It works on Mac, Linux, and Windows on any hardware and is up to 2x faster than llama.cpp. We're both software engineers and previously built an open source browser agent to 4k+ GH stars and 100k+ downloads. We increasingly wanted to run it on local models, but found that no inference engine worked for our use case. Inference engines today all m

Hacker News ·

Show HN: Nibia Fabric – Turn everyday computers into a shared AI compute cluster

I built NIBIA Fabric, an open-source distributed LLM inference system that pools CPU and RAM across macOS, Linux, and Windows machines. It builds on llama.cpp, with capacity-aware scheduling, adaptive memory reservation, persistent tensor caching, and an OpenAI-compatible API. I’ve validated the current alpha on three physical machines across several models, including a 30B-class Qwen model, as well as GPT-OSS 20B. Feedback on the architecture and use cases is very welcome.