Embed summaries, not code
Off-the-shelf embedders are mediocre on conceptual queries against raw code. LLM-generated summaries close that gap.
wdpkr
Semantic code search for AI agents. Taps through your codebase to find exactly where things live — "where does the commission system live?" rather than "find the string CommissionService."
wdpkr search "release commission payments to individual payees"wdpkr is not a replacement for grep/ripgrep. It’s the conceptual layer on top. The agent reads the actual files for ground truth — wdpkr’s job is to point and describe, not to ship source into the context window.
Why it works
AST-driven chunking
Tree-sitter parses files into meaningful symbols — functions, types, traits — across 8 languages, not arbitrary line splits.
Pluggable backends
Traits for VectorStore, Embedder, Summarizer, and Chunker. Swap providers without touching the pipeline.
CLI, not MCP
Any agent that can shell out can use it. JSON to stdout, errors to stderr.
Where to next