jz
jz's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @xinzzu appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the Memoria corpus
xinzzu/Memoria: Second brain offline for AI coding tools: capture sessions from Claude, Codex, Gemini, Copilot & more, recall anywhere via MCP +…
- Look up how Memoria implements ai-coding, ai-tools, claude-code, with answers cited to file and line.
- Reuse a worked example: the commit “FTS5 search + Float32 BLOB embeddings + SQL dedupe + list …” (12 files · JavaScript, TypeScript).
- Answer from Memoria's real JavaScript source instead of memory (AI, prompts and agents).
- How does Memoria implement ai-coding?
- What does web do in Memoria?
Search the GitHub repository xinzzu/Memoria with XERJ (https://hub.xerj.org/corpus/xinzzu--memoria). 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/xinzzu/Memoria Memoria && git -C Memoria checkout 715155fc646632890df13a6e6939de1a30cfe39f 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Memoria --url http://127.0.0.1:9200 --prefix memoria --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 xinzzu--memoria · AI, prompts and agents
Related corpora: xobotyi--cc-foundry-the-workflow-claude-md, s2n-tls, Dayifour/nexus, Alekla0126/alchemist-coder
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
xinzzu/Memoria
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/xinzzu)
Included with the author's permission (email, 2026-11-13), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.