Back to directory

sweet-search

A local, GPU-accelerated code search toolkit for AI coding agents that combines grep-style, semantic, and graph-based retrieval to cut tool calls and cost compared with plain grep and file reads.

sweet-search

sweet-search is a set of six code-retrieval tools, search, grep, find, semantic, trace, and read, built specifically for AI coding agents such as Claude Code and Codex, reached through MCP or direct integration. It indexes a repository once with a GPU-accelerated pipeline and then keeps the index current automatically as files change, including uncommitted edits, without requiring Docker or cloud services.

The project reports that using its tools instead of grep and file reads lowered cost and tool calls on a set of engineering tasks while keeping solve rates statistically similar. It runs on macOS and Linux, with a WASM fallback, and installs as a global npm package that wires itself into a coding agent's configuration during initialization.

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.