Terminal-native AI agent runtime — parallel orchestration, reactive subagents, MCP, autonomous supervision
GitHub-backed agent blueprints for Everruns
Vela agent layer: scoped scientific tasks (Literature Scout, Notes Compiler, Code Analyst, …) that emit signed proposals into a Vela frontier.
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.
The vela command-line tool: build, check, sign, replay, and publish scientific frontier state.
Core library for the Vela scientific knowledge protocol: replayable frontier state, signed canonical events, and proof packets.
Token-efficient Markdown structure CLI for agents
Fast, AST-based code-navigation: shape, public API, deps & call graphs, hybrid semantic search, structural rewrite, and log squeezing. MCP server included.
Symbiotic relationship patterns for ternary agents including mutualism, parasitism, and commensalism
Some of the stuff I've created while learning the 'State of the Art' in AI.
Multi-AI CLI team orchestrator
Emotion and personality engine — trait spectrums, mood vectors, archetypes, behavioral mapping