Toctsu

What an agent can do with the dsh-full-life-memory corpus

Toctsu/dsh-full-life-memory: A biomimetic memory plugin for DeepSeek Harness. Folds context into token clues and reconstructs memories, enabling infinite conversations…

• Look up how dsh-full-life-memory implements context-window, deepseek-harness, dsh-plugin, with answers cited to file and line.
• Reuse a worked example: the commit “add scene-specific overrides (qqbot, wechat, etc.)” (6 files · JavaScript, TypeScript).
• Answer from dsh-full-life-memory's real JavaScript source instead of memory (AI, prompts and agents).

• Where does dsh-full-life-memory handle “add scene-specific overrides (qqbot, wechat, etc.)”?
• How does dsh-full-life-memory implement context-window?
• What does test do in dsh-full-life-memory?

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.

corpus toctsu--dsh-full-life-memory · AI, prompts and agents
Related corpora: 12-factor-agents, agno, jidekaixin2dian/dsh-toolgate, justhalfbit/dsh-plugin-memory
AI search and retrieval with XERJ · Case study: reference coding for agents