Noah

What an agent can do with @noahc1510's commit to metahub-core

Tensorix/metahub-core: Local-first knowledge base and persistent memory for AI agents, with structured tables, Markdown docs, CRDT sync, CLI, WebUI, and REST API

• Look up how metahub-core implements agent-memory, ai-agents, bun, with answers cited to file and line.
• Reuse a worked example: the commit “add logo variants and appearance controls” (14 files · TypeScript).
• Answer from metahub-core's real TypeScript source instead of memory (AI, prompts and agents).

• Where does metahub-core handle “add logo variants and appearance controls”?
• How does metahub-core implement agent-memory?
• What does src/webui do in metahub-core?

Search the GitHub repository Tensorix/metahub-core with XERJ (https://hub.xerj.org/corpus/tensorix--metahub-core).
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/Tensorix/metahub-core metahub-core --filter=blob:none --no-checkout && git -C metahub-core sparse-checkout set --no-cone /apps/desktop/assets/ /apps/desktop/scripts/ /assets/brand/ /src/webui/ && git -C metahub-core checkout 06540f53a5ec6df48ff23f3faf93f1f4916252fc
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./metahub-core --url http://127.0.0.1:9200 --prefix metahub-core --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: AGPL-3.0. Read it for the approach only, do not copy code.

corpus tensorix--metahub-core · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, xobotyi--cc-foundry-javascript, burakdede/lorepack, sequico/server-noonien
AI search and retrieval with XERJ · Case study: reference coding for agents