Deanonymize anyone based on their public commenting or posting history & pattern.

AI agent to evaluate and score resumes.

Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

List of "only yours" cloud services for everyday needs 🏴

CNF generator in DIMACS format. It produces common families of CNFs.

My ISP tried to block this repo. 🤐 A truly peer-to-peer, end-to-end encrypted CLI chat that leaves NO logs. Perfect for... sensitive discussions. 🔥 Get it before it gets taken down

dCache - a system for storing and retrieving huge amounts of data, distributed among a large number of heterogenous server nodes, under a single virtual filesystem tree with a variety of standard a…

Ultrafast serverless GPU inference, sandboxes, and background jobs

A minimalist, distraction-free speed reading application built with Flutter & Supabase.

Algorithm powering the For You feed on X

Flux 2 image generation model pure C inference

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

dLLM: Simple Diffusion Language Modeling

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Implementation of self-certainty as an extention of ZeroEval Project

Super-fast Structured Outputs

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

Implementation of Java Spring Boot Security

Renderer for the harmony response format to be used with gpt-oss

Minimal CSS Framework for semantic HTML

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Efficient few-shot learning with Sentence Transformers

Simplified version of MHLA (RopelessMHLA) inspired from deepseek v2

An open-source AI agent that brings the power of Gemini directly into your terminal.

Model Context Protocol server for Vikunja task management. Enables AI assistants to interact with Vikunja instances via MCP.

Build Real-Time Knowledge Graphs for AI Agents

Leetcode Problems Solutions