DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let the agent file durable facts when a session ends with DSH Auto Memory

Turn on auto-summarize so a background model saves new durable facts after each session.

Who it is forA developer whose sessions produce useful decisions and facts that they never write down manually.

The problemImportant facts from a session are lost unless the user remembers to ask the agent to store them.

The outcomeWhen a root session ends, a background LLM files up to the configured number of durable new facts as memories.

What you need first

  • DeepSeek Harness (@deepseek-ai/dsh) version 0.1.5-rc.2 or newer, or the official desktop client (verified on 0.2.0-rc.2)
  • Node.js ^22.19 or >=24
  • A dsh profile to install the plugin into (the README uses the profile name demo)

Steps

  1. Open the profile's cordis.patch.yml file.
  2. Add an auto-memory entry with config that sets autoSummarize: true and autoSummarizeMaxMemories: 5.
  3. Keep maxBytes and the other values you need, because the config replaces wholesale.
  4. Run dsh --profile demo to restart the profile, then finish a session and check the memory folder.

Prompt for your agent

Edit the cordis.patch.yml for the DeepSeek Harness profile demo so the dsh-auto-memory config sets autoSummarize to true and autoSummarizeMaxMemories to 5. Expected output: after a session ends, new memory files appear under the memory folder. Verify that the new files contain durable facts only and that MEMORY.md lists them.

Caveat. Auto-summarize uses a background LLM and is off by default, so review the filed memories because the README does not describe how it judges what is durable.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page