nexus-kb
CLAUDE.md1 starsChanged 5 months agoMITView on GitHub
Enterprise Knowledge Hub is an open-source architecture workspace for an enterprise RAG and Knowledge Graph platform. The runnable implementation currently lives in qdrant-multi-node-cluster/. Read these files before making substantial changes: Documentation-only changes require manual link and heading review. Qdrant demo verification: Alternative:
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- mcp-maintainerSkill
- release-guardSkill
- repo-onboardingSkill
- deploySkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 7
Read these files before making substantial changes:
- Very specific: line 39
Follow .claude/rules/ for code style, API conventions, and testing.
- Distinctive: line 40
Do not commit secrets, local sessions, raw documents, model files, vector snapshots, or logs.
- Very specific: line 41
Keep architecture changes synchronized with docs/architecture.md.
- Very specific: line 42
Keep local overrides in CLAUDE.local.md.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude Code Project Guide
Project Context
Enterprise Knowledge Hub is an open-source architecture workspace for an enterprise RAG and Knowledge Graph platform. The runnable implementation currently lives in qdrant-multi-node-cluster/.
Read these files before making substantial changes:
README.mddocs/architecture.mdAGENTS.md
Repository Areas
- Root and
docs/: documentation, architecture, and governance. .claude/,.codex/,.agents/,.hermes/: AI-agent configuration and local automation.qdrant-multi-node-cluster/: Python and Docker Qdrant demo.
Commands
Documentation-only changes require manual link and heading review.
Qdrant demo verification:
cd qdrant-multi-node-cluster
make testAlternative:
cd qdrant-multi-node-cluster
python -m unittest discover -s testsRules
- Follow
.claude/rules/for code style, API conventions, and testing. - Do not commit secrets, local sessions, raw documents, model files, vector snapshots, or logs.
- Keep architecture changes synchronized with
docs/architecture.md. - Keep local overrides in
CLAUDE.local.md; this file is ignored by the root.gitignore.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

