vvooki

What an agent can do with the loomem corpus

vvooki-sys/loomem: Open-source context layer for LLM agents: a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex or any MCP client the…

• Look up how loomem implements ai-agents, embeddings, llm, with answers cited to file and line.
• Reuse a worked example: the commit “enforce fragment dates and finalize search evidence” (9 files · Rust, Python).
• Answer from loomem's real Rust source instead of memory (AI, prompts and agents).

• Where does loomem handle “enforce fragment dates and finalize search evidence”?
• How does loomem implement ai-agents?
• What does loomem-server do in loomem?

Search the GitHub repository vvooki-sys/loomem with XERJ (https://hub.xerj.org/corpus/vvooki-sys--loomem).
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/vvooki-sys/loomem loomem && git -C loomem checkout fdb1dae31dc9d9b074bafb9518592ab332edc4e2
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./loomem --url http://127.0.0.1:9200 --prefix loomem --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus vvooki-sys--loomem · AI, prompts and agents
Related corpora: candle, delta-rs, codecoradev/uteke, bobmatnyc/trusty-tools
AI search and retrieval with XERJ · Case study: reference coding for agents