Phina

What an agent can do with the contextweave corpus

Lucien-rose/contextweave: Long-term memory infrastructure for AI agents

• Look up how contextweave implements agent-memory, agent-memory-mcp, agent-memory-system, with answers cited to file and line.
• Reuse a worked example: the commit “Split runtime and admin MCP surfaces” (7 files · JavaScript, shell).
• Answer from contextweave's real JavaScript source instead of memory (AI, prompts and agents).

• Where does contextweave handle “Split runtime and admin MCP surfaces”?
• How does contextweave implement agent-memory?
• What does server do in contextweave?

Search the GitHub repository Lucien-rose/contextweave with XERJ (https://hub.xerj.org/corpus/lucien-rose--contextweave).
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/Lucien-rose/contextweave contextweave && git -C contextweave checkout 8951dd9ca6f0a5947f47503c39f6be92696db909
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./contextweave --url http://127.0.0.1:9200 --prefix contextweave --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 lucien-rose--contextweave · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, vanguard-context-burn, dreamforgestudiollc/EMET, youxi-huang/slice
AI search and retrieval with XERJ · Case study: reference coding for agents