OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Evaluation & Observability

Agentic OS — KbWen

Agentic OS is an MIT-licensed governance framework for AI coding agents that combines AGENTS.md rules, staged workflows, work-trail evidence, git hooks and CI checks to validate whether coding tasks meet defined planning, review, testing and shipping requirements.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentic OS — KbWen — OpenViST project profile in Agent Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when AI-generated code needs enforceable repository gates beyond the agent’s own completion report.

Who it is for

  • Developers using AI coding agents in repositories
  • Teams seeking repository-level evidence checks for agent-generated changes
  • Projects that want agent instructions reinforced by hooks and CI

Documented uses

  • Define coding-agent rules with AGENTS.md.
  • Require evidence for workflow phases such as planning, review and testing.
  • Detect leaked credentials before changes proceed.
  • Reject specified CI conditions such as a green test result when zero tests ran.
Before you choose

Requirements & limits

The repository is public and identifies an MIT license. It is described as usable on Linux, macOS and Windows through a CLI and self-hosted workflow.

  • Its core distinction is enforcement outside the agent: validators read work-trail evidence and hooks or CI can fail specified conditions.
  • It supports repository rules through AGENTS.md and names Claude Code, Codex, Cursor, GitHub Copilot and Antigravity.
  • The documented local pre-commit hook is opt-in and bypassable, while required CI checks provide the non-skippable merge floor described by the repository.
  • The supplied material does not document per-agent setup commands or implementation details.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add evidence-gated governance to an AI coding repository

Apply Agentic OS rules and validation to an AI coding workflow.

Before you start

  • A repository using Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, or another Markdown-reading agent.
  • A repository workflow that can use AGENTS.md rules and git hooks or CI.
  • Source documentation for Agentic OS.

Steps

  1. Add the repository’s Agentic OS governance rules through AGENTS.md.

  2. Use the documented workflow phases for the task, including planning, implementation, review, testing and shipping where applicable.

  3. Connect the validator to repository git hooks and CI checks.

  4. Require the documented checks to pass before the change proceeds.

Expected outcome

The repository has an evidence-gated workflow in which specified missing evidence, leaked secrets or invalid test claims can fail local or CI validation.

Guide limitations

  • The supplied documentation does not include configuration steps for each supported coding agent.
  • The local pre-commit hook is opt-in and can be bypassed with --no-verify.
  • Security scanning jobs are not required merge checks unless branch protection adds them.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Agentic OS — KbWenDefine coding-agent rules with AGENTS.md.CLI, Linux, macOS, Self-hostedThe repository is public and identifies an MIT license. It is described as usable on Linux, macOS and Windows through a CLI and self-hosted workflow.
Harness ScoreMeasure the presence and structure of agent guidance, skills, hooks, feedback tools and safeguards.CLIThe project is documented as a CLI and is MIT-licensed. The README shows invocation through `npx harness-score` and references a GitHub Action.
AgenttrailSee which project components and files are changing.CLI, DesktopKitchen setup requires Node.js 20 or later, a browser with WebGL and a local project folder. The README describes Kitchen as a public experimental preview.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
KbWen/agentic-os · Official homepage title · retained in its source language
How we review sourcesSuggest a correction