saracura
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation
What XERJ indexed
Snapshot
The whole repository at commit 5c06fd14a3 (2026-10-21). main is 14 commits ahead.
Selected work
“Make PT-BR benchmark evaluation and submission reproducible”. 4 files, 1,485 lines in tests, research.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-26. 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
calibrationdecision-enginelocal-aimachine-learningmultilingualopen-sourcept-brpython
Example questions
- How does saracura implement calibration?
- Where does saracura handle “Make PT-BR benchmark evaluation and submission reproducible”?
- What does research do in saracura?
Inside the indexed corpus
- 362 files, 6.3 MB in total, about 17.7 KB per file.
- The selected commit changed 4 of those files (1.1%).
- On GitHub since 2026-09-21, last push 2026-10-21, 167 commits on main.
- The pin is 14 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for felhen-ai/saracura on 2026-10-31, and the LICENSE file at commit 5c06fd14a3 was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Antonio Mello (@antonio-mello-ai) has 12 selected repositories on the hub.
Their other repository pages: antonio-mello-ai/mcp-proxmox, antonio-mello-ai/mcp-pfsense, antonio-mello-ai/mcp-redis-monitor, antonio-mello-ai/crewdock, antonio-mello-ai/iterm-ai-agents-bundle, antonio-mello-ai/mcp-airflow.
Using XERJ with saracura
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best MCP servers for local code search in 2026, compared
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones felhen-ai/saracura at the pinned commit and indexes it on your machine.
Search the GitHub repository felhen-ai/saracura with XERJ (https://hub.xerj.org/corpus/felhen-ai--saracura). 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/felhen-ai/saracura saracura && git -C saracura checkout 5c06fd14a3f98cb08158fa02d842b2caabcf242a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./saracura --url http://127.0.0.1:9200 --prefix saracura --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.
Related
Antonio MelloAI, prompts and agents corporahead-qavuln-fix-commitskotaemonaawhan0/ModelDockjonsnow273/MeganAINandhaKishorM/laya
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.