memoria-nox
Self-hosted memory for LLM agents - one SQLite file, zero services, MIT. Hybrid retrieval (FTS5 + sqlite-vec + RRF) with pain-weighted salience and a knowledge graph. Under matched embeddings, outperforms Mem0 on LoCoMo and LongMemEval. Your data, your provider, your disk
What XERJ indexed
Snapshot
The whole repository at commit c39bfe3322 (2026-10-27). main is 22 commits ahead.
Selected work
“passe de oraculo sobre as 9: o limite de -14,1% e na verd…”. 3 files, 343 lines in audits, eval.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
better-sqlite3gemini-embeddingshybrid-searchknowledge-graphllmmemory-systemmulti-agentsqlite
Example questions
- How does memoria-nox implement better-sqlite3?
- What does audits do in memoria-nox?
- Show the gemini-embeddings code in memoria-nox.
Inside the indexed corpus
- Languages by size: Python 52%, TypeScript 28.2%, Shell 8.7%, TeX 3.4%, JavaScript 3.2%.
- On GitHub since 2026-04-20, last push 2026-10-29, 1,411 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 MIT for totobusnello/memoria-nox on 2026-10-29, and the LICENSE file at commit c39bfe3322 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Totó Busnello (@totobusnello) has 1 selected repository on the hub.
Using XERJ with memoria-nox
- Full-text search a SQLite database (FTS5 alternative) memoria-nox is tagged sqlite on GitHub.
- Search JSON and JSONL logs plus gzip logs in one folder memoria-nox is tagged observability on GitHub.
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones totobusnello/memoria-nox at the pinned commit and indexes it on your machine.
Search the GitHub repository totobusnello/memoria-nox with XERJ (https://hub.xerj.org/corpus/totobusnello--memoria-nox). 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/totobusnello/memoria-nox memoria-nox && git -C memoria-nox checkout c39bfe33221e9d1d1ceb36e7372df211e5cc0e8e 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./memoria-nox --url http://127.0.0.1:9200 --prefix memoria-nox --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: MIT. Keep the copyright notice and credit the authors.
Related
Totó BusnelloAI, prompts and agents corporaagentopsagentscopegraphragOussama-zbir/retrieval-evaluation-labCipher208/a-memoryDeepnar/ice
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.