isyyue

What an agent can do with the dsh-ai-memory corpus

Isyyyue/dsh-ai-memory: DeepSeek Harness 插件：可审计的长期判断记忆、确定性取代、未完成问题、用户确认的人格演化与知识图谱。 Auditable judgment memory for DSH agents

• Look up how dsh-ai-memory implements bi-temporal, deepseek-harness, dsh-plugin, with answers cited to file and line.
• Reuse a worked example: the commit “give memory unfinished questions, thinking cycles and a self model” (19 files · JavaScript).
• Answer from dsh-ai-memory's real JavaScript source instead of memory (AI, prompts and agents).

• Where does dsh-ai-memory handle “give memory unfinished questions, thinking cycles and a self model”?
• How does dsh-ai-memory implement bi-temporal?
• What does test do in dsh-ai-memory?

Search the GitHub repository Isyyyue/dsh-ai-memory with XERJ (https://hub.xerj.org/corpus/isyyyue--dsh-ai-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/Isyyyue/dsh-ai-memory dsh-ai-memory && git -C dsh-ai-memory checkout 1443bab4858a603f9feec59b5b54b5f9d25e41d5
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dsh-ai-memory --url http://127.0.0.1:9200 --prefix dsh-ai-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 isyyyue--dsh-ai-memory · AI, prompts and agents
Related corpora: pearjelly/deep-blend, xcisxc29/dsh-qq-plugin
AI search and retrieval with XERJ · Case study: reference coding for agents