AI Agent Hub
Back to plugins
🧠

dsh-memory

Memory Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install boomzikazita/dsh-memory

Paste the following prompt into your AI chat to install this plugin:

Install this plugin in DeepSeek Harness by running dsh plugin install boomzikazita/dsh-memory; the full source is available at https://github.com/boomzikazita/dsh-memory .

About this plugin

Every DeepSeek Harness session is stateless; close the terminal and the context is gone. dsh-memory adds a persistent memory layer so the model still remembers confirmed rules, corrected preferences, and distilled skills across days and projects.

The write path is proposal-based: memory_suggest enqueues a candidate, budget checks and sensitive-pattern screening run, and only memory_confirm promotes it into L1. At recall time, five RRF channels - rule files, session full-text index, semantic search, wiki, and time-window - are fused into a single ranked evidence ledger with per-item trust labels. Secrets are isolated in a Fernet-encrypted vault; plaintext never appears, only vault references. A session-transcription module incrementally indexes logs and extracts correction signals for skill distillation.

Built for developers who collaborate with dsh long-term, manage multiple rule sets and credentials, and want to turn ad-hoc experience into reusable, auditable skills.

Use Cases

  • Retain confirmed user preferences and project rules across sessions
  • Securely store and retrieve API keys and sensitive credentials in an encrypted vault
  • Extract correction signals and reusable skills from historical session logs

Best For

  • Developers collaborating with dsh on long-running multi-round projects
  • Tech leads needing centralized management of multiple rule sets and credentials
  • Engineers who want to turn ad-hoc experience into auditable, reusable assets