AXON — the formal cognitive language: a deterministic, proof-carrying AI runtime. Native Rust lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the runtime: typed channels (π-calculus mobility, capability extrusion), algebraic effects via Free Monad CPS handlers, lease kernel + reconcile loop, the Epistemic Security Kernel, Trust Types, Proof-Carrying Code (independently verifiable proof objects), and the closed-catalog extension mechanism. Crate publishes as `axon-lang`; library import is `use axon::*` so existing call sites keep working unchanged.
Rust bindings for the Listen Notes Podcast API
Semantic code navigation for AI agents
A surgical port killer - find and terminate processes using specific ports
Smart Tree - An intelligent, AI-friendly directory visualization tool
macOS Accessibility API CLI tool — a Playwright/Puppeteer-style CLI for native macOS apps
Deep Reinforcement Learning Framework
Kowalski Web Agent: A Rust-based agent for interacting with Ollama models
Rust code navigation built for AiDX — AST-aware, MCP-native, token-efficient.
Deep reinforcement learning algorithms for rlevo (internal crate — use `rlevo` for the full API)
Agent coordination primitives + multi-agent patterns for the Brainwires Agent Framework — communication hub, file/resource locks, task manager/queue, git coordination, contract net, saga, optimistic concurrency, market allocation, workflow graph, three-state model. LLM-driven workhorses live in `brainwires-inference`.
This crate provides tools for exploring the edge of a performance mode for complex systems testing, analysis, and optimization. A performance mode is an abstract characteristic of the system, which can be anything from an Autonomous Vehicle's safety, a function throwing exceptions, or a threshold being exceeded. Any form of binary classification of the input space can be used to explore the boundary between the classifications. Applications include falsification, training data generation, region of validity analysis, and much more.