llm-ingestion-okf/llms.txt
Kjell Tore Guttormsen e882d0bc23 docs: add llms.txt entry point (D2b, operator decision 2026-08-21)
Structured entry point for an AI agent already in the repo, per the
llms.txt convention (llmstxt.org): H1, blockquote summary, and the
repo's one start command in copyable form. The command is byte-identical
to README's first fenced code block, not a rewritten variant, so the
two cannot drift apart silently.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011mVhrxD21mPtaLMrGdixUq
2026-08-21 11:28:25 +02:00

13 lines
506 B
Text

# llm-ingestion-okf
> Shared OKF (Open Knowledge Format) ingestion library: spec-based connectors, bundle inbox, and external-bundle import. Security delegated to llm-ingestion-guard.
Install with uv (one command; it resolves the guard dependency on its own):
```
uv pip install "llm-ingestion-okf @ git+https://git.fromaitochitta.com/open/llm-ingestion-okf.git@v0.4.0"
```
## Optional
- [README](README.md): the plain-pip alternative, phase status, requirements, and the upstream OKF version policy.