DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-honcho-sync

DeepSeek Harness plugin that syncs conversations to a self-hosted Honcho v3 memory service for persistent cross-session recall.

UI & ProductivityDeveloper Tools
5GitHub Stars0ForksUpdated2026-08-20

Install

$ dsh plugin --profile web add npm:@nanpaidashi/dsh-honcho-sync dsh web

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-honcho-sync is a DSH web-profile integration for self-hosted Honcho v3. It automatically syncs conversation turns, recalls memory across sessions, injects relevant memory context into prompts, and exposes Honcho operations as DSH tools.

Key Capabilities

  • Auto-syncs conversation turns to Honcho with debouncing and persisted sync cursors.
  • Performs hybrid semantic recall across messages and conclusions.
  • Injects peer cards, representations, session summaries, and recall results into the system prompt when auto-recall is enabled.
  • Exposes tools for recall, deep reasoning, saving memories, and retrieving compressed session context.
  • Supports additional Honcho operations including search, peers, sessions, messages, conclusions, health checks, dreaming, and queue status.
  • Supports per-directory sessions by default or a shared global session strategy.

Useful For

  • Preserving AI conversation memory across DSH sessions and restarts.
  • Recalling prior project context when returning to a working directory.
  • Searching stored messages and derived conclusions in a self-hosted memory service.
  • Providing an agent with user and agent peer context at the start of a session.

Who It Fits

  • DeepSeek Harness web-profile users.
  • Users operating a self-hosted Honcho v3 instance.
  • Developers who want persistent, workspace-scoped AI memory.

Documented Limitations

  • Requires DeepSeek Harness with the web profile, Node.js 18 or later, and a running self-hosted Honcho v3 instance.
  • HONCHO_URL and HONCHO_WORKSPACE must be configured through DSH service environment variables.
  • The README states there is no settings panel; advanced defaults require editing src/index.mjs.
  • Deep reasoning via honcho_ask is documented as slower than recall.
  • Memory is partitioned by working directory under the default per-directory session strategy.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 1 peer, and 0 optional dependencies.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
nanpaidashi/dsh-honcho-sync
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
83e7792 · 2026-09-14

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
5GitHub stars
Forks
0
Open issues
0
Last commit
2026-08-20
Last release
No release detected
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app