server-noonien
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph
What XERJ indexed
Snapshot
The whole repository at commit 7ae08a4053 (2026-10-16). main is 12 commits ahead.
Selected work
“wait out contention, and name the corruption”. 10 files, 305 lines in test, src/graph, src/sync.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. 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
crdtknowledge-graphlocal-firstmcpmemorymodel-context-protocolopencodeserverless
Example questions
- How does server-noonien implement crdt?
- Where does server-noonien handle “wait out contention, and name the corruption”?
- What does src/graph do in server-noonien?
Inside the indexed corpus
- 134 files, 1.3 MB in total, about 10.0 KB per file.
- The selected commit changed 10 of those files (7.5%).
- Languages by size: TypeScript 98.1%, JavaScript 1.7%, Dockerfile 0.2%.
- On GitHub since 2026-10-08, last push 2026-10-29, 81 commits on main.
- The pin is 12 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MPL-2.0 for sequico/server-noonien on 2026-10-31, and the LICENSE file at commit 7ae08a4053 was reviewed as MPL-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
sequicompany (@sequico) has 1 selected repository on the hub.
Using XERJ with server-noonien
- Code search MCP for Claude Code: cite file:line, not grep server-noonien is tagged mcp on GitHub.
- What is an MCP memory server?
- What is agentic memory? A plain answer server-noonien is tagged agent-memory on GitHub.
- XERJ vs Mem0, Zep, Letta and Cognee for agent memory
The prompt
Paste it into your AI agent. It clones sequico/server-noonien at the pinned commit and indexes it on your machine.
Search the GitHub repository sequico/server-noonien with XERJ (https://hub.xerj.org/corpus/sequico--server-noonien). 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/sequico/server-noonien server-noonien && git -C server-noonien checkout 7ae08a40535471edb92c1dbb45faaee316ab0cdd 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./server-noonien --url http://127.0.0.1:9200 --prefix server-noonien --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: MPL-2.0. Read it for the approach only, do not copy code.
Related
sequicompanyAI, prompts and agents corporadunorth595--ai-agent-memoryjaeger-docs12-factor-agentsYusenZhang0601/context-canopyvvooki-sys/loomemTensorix/metahub-core
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.