Kaut — AI skill for Claude Code
KAUT — Knowledge Actualization Under Trust: self-maintaining, AI-first project knowledge for AI agents.
How to install Kaut
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open yurgeno/kaut and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Kaut does
KAUT — Knowledge Actualization Under Trust: self-maintaining, AI-first project knowledge for AI agents. Source-bound docs, git-computed freshness verdicts, a gated write path, zero dependencies, MCP server included.
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Codex Plugin — 's /codex:adversarial-review command 9.6k ★
- macOS App Skills — AI coding agent skills for building, shipping, and maintaining native macOS apps 657 ★
README
KAUT — Knowledge Actualization Under Trust
[](https://github.com/yurgeno/kaut/actions/workflows/test.yml) [](https://github.com/yurgeno/kaut/releases) [](LICENSE)    [](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)
**Makes legacy codebases AI-native.** KAUT is self-maintaining, AI-first documentation for your project — a knowledge layer that makes undocumented, weak-context code legible to AI agents. Not a memory of conversations — a knowledge base about the system itself: what it does, how it is structured, and why. It turns what agents learn while working into living documentation — so no session starts from zero.
Zero-dependency Node.js (≥ 20, developed on 24), Apache-2.0. **Developed and tested on macOS and Linux** (CI runs Linux, Node 20 and 24); Windows is not supported.
**A complete, standalone product.** One `git clone` is the whole install; point your harness at the bundled MCP server (or call the CLI from any skill/prompt) and it works — no orchestrator, no framework, no services, no accounts, nothing else to deploy. It composes with the sibling [TAUT](https://github.com/yurgeno/taut) orchestration framework (TAUT drives agents, KAUT is what they know) — but that integration is optional, not a dependency.
**Status: v0.9.0 — the full loop is live.** Reading: `lookup` (one-call ready answer) with freshness verdicts (merge-base-anchored, never crying "fresh" when unsure), trust tiers, and the `altitude` co
Related Skills
Auto Guard
A cached auto command review guard for AI coding agents — rules, memory and LLM verdicts (allow/deny/ask) befo
Claude Code Blueprint
Battle-tested reference architecture for Claude Code power users. Specialized agents with model tiering, nat
Multipov Plan
Run a multi-agent design-doc review on $ARGUMENTS (path to a markdown design doc, typically docs/plans/YYYY-MM
Gatewright
Open-source task tracker for AI coding agents (Claude Code, Codex, Cursor, Copilot, Gemini CLI). A git-tracked
Chronicle
Sync AI coding agent session history (Pi, Claude Code) across machines using path canonicalization and Git-bac
Planx
Write a self-contained chapter plan to docs/plans/ / / /<1NN>- / for another AI to write the prose.
Related Agents
Content Eeat Analyst
Read-only content quality specialist. Use proactively during an audit to evaluate E-E-A-T (author identity, cr
Prose Asserter
Judges a prose-test walk against the case's expected path and the code-computed world delta, returning a four-
Digest
Generic digest compiler. Input: path to project config file and number of days. Reads pre-computed per-commit