Back to directory

session-indexer

A per-project semantic search tool over a developer's own Claude Code session history, so a new session can recall what was decided in past ones instead of needing to be re-explained.

session-indexer

session-indexer builds per-project semantic search over Claude Code session history. It indexes JSONL transcripts into a SQLite store scoped to one project, retrieves matching passages using bge-m3 embeddings through Ollama with an FTS5 BM25 fallback, and can inject relevant past context automatically at the start of a new session.

It is deliberately scoped to a single developer on a single machine rather than shared team memory, so a corrupted or lost database only affects one project and is fully recoverable by re-running the indexer against the original transcripts. It is written in Go, needs a recent Go toolchain to build, and uses jq for JSON formatting in its hooks.

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.