npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

dsh-patchouli-native-context-service

v0.1.8

Published

Native local context indexing and retrieval for Patchouli

Readme

dsh-patchouli-native-context-service

Official Patchouli service for building and retrieving native local context from DeepSeek Harness sessions, workspaces, and related sources. It is intended for ordinary Sessions as well as integrations that add richer identity or visibility semantics, such as Agent Fleet.

The service is organized as an index -> algo -> retrieve pipeline. It indexes bounded Session history, visible Workspace and project files, stored Artifact metadata/text, and policy-aware Git snapshots when a Git reader is available. Those records are stored as Patchouli knowledge and exposed through bounded fast retrieval. Standard retrieval uses the configured DSH model to plan a bounded set of Fast queries and synthesize cited evidence. Deep retrieval remains an optional runner and falls back to Standard or Fast when it is unavailable.

memory_retrieve receives a common { answer, references, truncated } result at every effort level. Fast retrieval formats its ranked evidence as numbered citations and omits internal ranking details by default. Pass metadata.includeRawHits: true when the complete ranked hit records are needed.

Artifact bytes remain in Patchouli's artifact store; native context records keep only visible text, metadata, and source references. Git indexing is disabled until the host provides a read-only, policy-aware reader.