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.

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.

RAG parameter sweep experimentation tool — systematically evaluate vector databases, embedding models, chunking strategies, and retrieval methods using any Vector database. Supports both Voyage AI (hosted) and local sentence-transformers models.

Give your AI a perfect, infinite memory. A local-first, zero-LLM memory system and Model Context Protocol (MCP) server designed to give AI assistants (like Claude, ChatGPT, and custom agents) a searchable, structured "Memory Palace."

A comprehensive Pre-RAG prototype dashboard for document parsing, multi-method chunking, vector embedding generation, and hybrid search exploration. Built with React and powered by in-browser ML models.

The design intelligence runtime for AI agents. 49 rules. Zero LLM. MCP-native. Give your agent eyes.

Deterministic reasoning assurance engine for AI agents. Fast (<5ms), zero-cost verification. Best-in-class for arithmetic, logic, and hallucination detection.

Persistent memory MCP server for AI coding agents like Claude Code. Zero-LLM, local-first (SQLite + FTS5), proactive recall by file path. 12 MCP tools, 113 tests. The MEMORY.md alternative that stays constant-cost at 10,000+ memories.