Starred repositories
Interactive architecture diagrams for codebases
Cloud replacement for vacuum robots enabling local-only operation
Nucleus is the library running at the core of Osmium, enabling large scale distributed actor systems
An agentic skills framework & software development methodology that works.
OpenTofu lets you declaratively manage your cloud infrastructure.
Zygo is a Lisp interpreter written in 100% Go. Central use case: dynamically compose Go struct trees in a zygo script, then invoke compiled Go functions on those trees. Makes Go reflection easy.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Portable, lightweight and embeddable WebAssembly runtime in C
Single-pass SSA bytecode compiler and threaded-code stack VM for a sandboxed Python subset: NaN-boxed values, inline caching, super-instruction fusion, pure-function memoization, mark-sweep GC. Cov…
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
The headless browser for AI agents and web scraping
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
C* (C-Asterisk) is a custom, high-performance programming language. It uses LLVM and native I/O bypasses to run Deep Learning models from scratch 100x faster than Python.
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
Self-hosted API rate limit router for spiky agentic traffic
NoSQL data store using the Seastar framework, compatible with Apache Cassandra and Amazon DynamoDB
A from-scratch compiler, assembler, and RISC-V VM, all running in real time in your browser.
MiniOS ESP is a FreeRTOS-based, Unix-like command-line operating system for ESP32 and RP2350 microcontrollers with ST7789 TFT displays, featuring kernel-level process management, a feature-rich int…
Distributed WASM runtime. Workloads place themselves over a zero-trust mesh. One static binary.
Chaos testing, network emulation, and stress testing tool for containers
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
Three lines of code to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDF…
FlashKDA: high-performance Kimi Delta Attention kernels