Formal architecture descriptors, neuro-symbolic code generation, and AI agent orchestration
The Homoiconic Context: S-Expression Architecture Descriptors as Navigation Primitives for AI Coding Agents
Formal architecture descriptors (intent.lisp) as navigation substrate for AI coding agents. Controlled experiments show 33–44% step reduction (d=0.92) with architectural context, while S-expressions emerge as the only format without a fatal flaw across parsing, generation, and error resilience.
Neuro-Symbolic Code Generation via S-Expression Intermediate Representation and Deterministic Harness Engineering
A neuro-symbolic architecture that constrains LLMs to output S-expressions, validates against typed IR defined as Rust enum whitelists, and deterministically assembles guaranteed-compilable code. 75% Pass@1 compilation rate vs 62% for raw LLM generation.
Multi-Agent Orchestration Daemon: Semantic Terminal Understanding, Persistent Knowledge, and 71 MCP Tools for AI Coding Agents
A Rust daemon (111K lines, 10 crates) that manages 1 foreground + N background AI coding agents through semantic PTY parsing, a 37-table knowledge base with hybrid FTS5 + embedding search, 18 background workers, and 71 MCP tools across 4 domains.