dsh-full-life-memory

A biomimetic memory plugin for DeepSeek Harness. Folds context into token clues and reconstructs memories, enabling infinite conversations…

A new way for AI to search for data
View on GitHub
4GitHub stars

JavaScript, TypeScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 03b487ef29.

Selected work

Toctsu
@Toctsu

“add scene-specific overrides (qqbot, wechat, etc.)”. 6 files, 622 lines in the project root, test.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-11-01. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

context-windowdeepseek-harnessdsh-pluginllmmemory

Example questions

The prompt

Paste it into your AI agent. It clones Toctsu/dsh-full-life-memory at the pinned commit and indexes it on your machine.

Search the GitHub repository Toctsu/dsh-full-life-memory with XERJ (https://hub.xerj.org/corpus/toctsu--dsh-full-life-memory).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Toctsu/dsh-full-life-memory dsh-full-life-memory && git -C dsh-full-life-memory checkout 03b487ef2925f729356d49f497974c8ac1e9bb3b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dsh-full-life-memory --url http://127.0.0.1:9200 --prefix dsh-full-life-memory --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.