metahub-core
Local-first knowledge base and persistent memory for AI agents, with structured tables, Markdown docs, CRDT sync, CLI, WebUI, and REST API
What XERJ indexed
Snapshot
The whole repository at commit 06540f53a5 (2026-10-21). main is 22 commits ahead.
Selected work
“add logo variants and appearance controls”. 14 files, 507 lines in src/webui, apps/desktop, assets.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-29. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: approach only
agent-memoryai-agentsbunclicontext-engineeringcrdtknowledge-baselocal-first
Example questions
- How does metahub-core implement agent-memory?
- Where does metahub-core handle “add logo variants and appearance controls”?
- What does src/webui do in metahub-core?
Inside the indexed corpus
- 636 files, 13.4 MB in total, about 21.6 KB per file.
- The selected commit changed 14 of those files (2.2%).
- Languages by size: TypeScript 91.2%, CSS 4.4%, HTML 4.2%, Shell 0.1%, JavaScript 0.1%.
- On GitHub since 2026-05-26, last push 2026-10-28, 424 commits on main.
- The pin is 22 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported AGPL-3.0 for Tensorix/metahub-core on 2026-10-31, and the LICENSE file at commit 06540f53a5 was reviewed as AGPL-3.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Noah (@noahc1510) has 1 selected repository on the hub.
Using XERJ with metahub-core
- What is agentic memory? A plain answer metahub-core is tagged agent-memory on GitHub.
- XERJ vs Mem0, Zep, Letta and Cognee for agent memory
- Full-text search a SQLite database (FTS5 alternative) metahub-core is tagged sqlite on GitHub.
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
The prompt
Paste it into your AI agent. It clones Tensorix/metahub-core at the pinned commit and indexes it on your machine.
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 && 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.
Related
NoahAI, prompts and agents corporadunorth595--ai-agent-memoryxobotyi--cc-foundry-javascriptkube-hunteraistastudio/mycsequico/server-noonienburakdede/lorepack
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.