Freya is a proactive personal assistant with a unified context graph layer

Optimize prompts, code, and more with AI-powered Reflective Optimization

from vibe coding to agentic engineering - practice makes claude perfect

Fully automatic censorship removal for language models

Build product integrations with AI.

Micro second messaging that stores everything to disk

C99 library for PO-32 acoustic transfers and drum synthesis.

AI agents running research on single-GPU nanochat training automatically

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Binary Proofs, Blazing Fast

Collaborative editing for ProseMirror

A framework for collecting and analyzing prediction market data, including the largest publicly available dataset of Polymarket and Kalshi market and trade data.

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Agent S: an open agentic framework that uses computers like a human

double (dostoevsky reference) local memory system for agents

An inky color scheme for prose and code.

A native music client for Jellyfin and Navidrome/Subsonic

An agentic skills framework & software development methodology that works.

A delightfully minimal, yet remarkably powerful AI Shell Assistant.

Context layer platform in your infrastructure

🦔 PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture…

the ps utility, with an eBPF twist and container context

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

A portable fork of the high-performance regular expression matching library

High-performance regular expression matching library

BareMetal for the private/public cloud

A unified interface for AI in your terminal.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.