lintlang is a static linter for AI agent configs, tool descriptions, and system prompts that runs zero-LLM quality gating in CI. Catches language-level failures (vague tool descriptions, missing stop conditions, schema gaps) before they reach runtime, with deterministic regex + structural detectors and no model calls.
Deterministic code synthesis operator — zero LLM in the loop. 8-color algebraic type system, 7-pass causal inference, 7-layer verification, 9-phase autonomous engagement. Substrate validated across 9 IEEE 2026 papers + IBM z/OS production assessment.
fidelis is zero-LLM agent memory for Claude Code and AI agents: a local-first memory layer whose default retrieval path uses BM25, dense vectors, and reciprocal rank fusion with no LLM call. It returns your original passages verbatim instead of paraphrasing and runs fully local. Benchmarked on LongMemEval-S. MIT, by Hermes Labs.
