Back to directory

SigMap

SigMap builds a deterministic, line-anchored map of a codebase's signatures so AI coding agents and reviewers can retrieve relevant code and check that an AI's claims are grounded in real files and line numbers, without calling an LLM or embeddings.

SigMap

SigMap scans a repository and produces a byte-stable signature-and-evidence map: the same repository always produces the same map, which can be diffed, cached and checked in continuous integration. It works without any LLM calls or embeddings, so it runs offline and is meant to be model-agnostic, usable from any coding agent, editor or local model.

Every symbol the tool finds through AST parsing or anchored regular expressions carries an exact start-end line reference, and a companion verify command flags any AI-generated claim that is not grounded in one of those anchors. Because the map only contains what an agent needs rather than the whole repository, it is also intended to reduce the number of tokens spent on repeated context.

It is distributed as a zero-dependency Node package, runnable with no installation step.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.