chunxiaoxx / nautilus-compass
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
Why this job: says: benchmark; topics: evaluation, benchmark
What it does
This project now also powers the independent judging layer of the Nautilus platform — preregistered criteria, three-state verdicts, negative results published as-is:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 1,257
- +4 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v3.3.0
- Released 37 days ago
- Built with
- Python
- 73% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 4% closed
- 23 still open
- Pull requests
- 24 merged
- 10 waiting
- Releases
- 9
- 9 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| agentevals-dev / agentevals | 169 | 5 days ago | Apache-2.0 | No downloads |
| AMAP-ML / LoopArena | 154 | 27 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 73%
- HTML 17%
- TypeScript 4%
- Shell 3%
Topics
- a2a
- agent-memory
- agentic-ai
- claude-code
- cross-agent
- mcp
- nautilus
- llm
- local-first
- long-term-memory
- memory-layer
- rag
Project record
- JobEvals and observability
- StatusListed
- Commits2,792
- Forks35
- Watching19
- Stars in 28 days+7
- CreatedApr 27, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026