YAIBOS
Talk to Samuel

Scorecard

How existing tools compare

Qualitative benchmark of 13 AI business operating systems, agent harnesses, second-brain apps, and workflow platforms against the six YAIBOS requirements for small businesses.

13 projects graded · Updated October 2026 · Suggest a project or correction ↗
What the grades mean: These letter grades do not judge overall engineering quality or developer usefulness. They compare how well each tool fits founder-led small businesses across the six YAIBOS pillars: plain-file ownership, non-technical usability, portable skills, bring-your-own-subscription, permissions, and harness portability.

Criteria (rated 0 to 5)

No terminal Non-technical users can run skills and edit notes from a graphical app.
Portable skills Markdown procedures with lifecycle and approval rules (Base), plus a launch dashboard and run history (Cockpit).
Own subscription Each user runs agents on their own AI plan through the official client, or their own API key.
Second brain Plain Markdown the owner controls, agent entry file, and tools to keep knowledge fresh.
Permissions & safety Authorization and untrusted-input rules (Base); enforced permissions per role belong to Team.
Portability Second brain as the single source of truth, harness and model switching, and a tools registry.
Sovereign AI Business OS & Cockpit Grade A

YAIBOS (Second Brain & Cockpit)

↗

Multi-Harness Layer (Claude Code / Codex / OpenCode / Antigravity)

Low-tech Markdown AI Business OS built by Samuel Michelot and set up with founders in the AI Bootcamp: AGENTS.md entry point, Projects, Roles, Resources, SOPs, Tools.md, named role agents with private memory, cross-harness synchronization, and a local visual Cockpit.

Verdict: Combines a durable, plain-file Base that never locks you in with a local desktop Cockpit (3D graph, SOP time-saved tracking, browser Markdown editor, Git activity review, and 1-click assistant handoff). Multi-user server RBAC is planned for larger teams.
Criterion 0–5
No terminal
4
Portable skills
5
Own subscription
5
Second brain
5
Permissions & safety
3
Portability
5

Strengths

  • ✓ Low-tech sovereign foundation: 100% plain Markdown files (AGENTS.md, Projects, Roles, Resources, SOPs, Tools.md) that work across Claude Code, Codex, OpenCode, and Antigravity.
  • ✓ Local YAIBOS Cockpit launched from a desktop icon: 3D second-brain graph, SOP time-saved analytics, role agents (Hugo, Max, Laura, Marc, Emma), embedded Markdown editor, and visual Git activity review with 1-click undo.
  • ✓ 100% Bring-Your-Own-Subscription (BYOS) through official vendor harnesses with zero token markup, plus automated weekly maintenance and non-destructive template updates.

Gaps vs YAIBOS

  • – Currently available only through the live AI Bootcamp rather than as a self-serve public download.
  • – Enforced multi-user folder RBAC is on the roadmap; current setups focus on founders and small businesses.
  • – Requires initial setup of at least one supported AI harness (such as Claude Desktop/Code or Codex).
Sovereign Desktop AI Workspace & Vault UI Grade B+

Kairos (formerly JARVIS, david-darr/kairos)

↗

Custom Bespoke Engine (No Open Harness)

Self-hosted, open-source AI workspace with multi-model chat, automations, and a Markdown second-brain viewer. Rebranded from JARVIS to Kairos with the v2.0 release, featuring an editorial light UI, Forge coding environment, and native desktop installers.

Verdict: Fits YAIBOS requirements for local file ownership and desktop delivery on Windows PC and Mac. It uses a custom runtime with its own maintenance needs.
Criterion 0–5
No terminal
5
Portable skills
3
Own subscription
4
Second brain
4
Permissions & safety
1
Portability
4

Strengths

  • ✓ Packaged desktop releases for Windows PC, macOS, and Linux that do not require a terminal.
  • ✓ Embedded Markdown vault graph visualization in Library directly inside the workspace.
  • ✓ Chats, memory, notes, and automations live in local files you own.

Gaps vs YAIBOS

  • – Not based on an open-source harness (such as DSH / Cordis): it uses a custom Python and Electron runtime, so it does not benefit from community harness plugins, fixes, or shared ecosystem improvements.
  • – Single-user desktop focus lacking multi-user team RBAC and folder-scoped permissions.
  • – Automations are not yet standardized into business skill cards with duration and ROI telemetry.
  • – Evolving plugin ecosystem under the new v2.0 architecture.
Kairos 2.0 Home: workspace dashboard with vault access, daily briefing, agents, and model status
Kairos 2.0 Home: workspace dashboard with vault access, daily briefing, agents, and model status
Kairos 2.0 Tasks: automation routines, event triggers (webhooks/GitHub pushes), and execution history
Kairos 2.0 Tasks: automation routines, event triggers (webhooks/GitHub pushes), and execution history
Kairos 2.0 Library Vault: interactive graph view of Markdown notes grouped by Projects, Resources, Personal, and Learning
Kairos 2.0 Library Vault: interactive graph view of Markdown notes grouped by Projects, Resources, Personal, and Learning

Screenshots from the project's README (source).

Obsidian Multi-Agent Harness & Skill Standard Grade B+

OBSIA (kevines-ods/OBSIA)

↗

Multi-Harness Layer (Claude Code native / OpenCode / Aider)

An open file-based multi-agent framework. Agents, skills, scheduled tasks, and memory live in plain Markdown. It includes a modular installer that uses host context and a security contract for each agent.

Verdict: The primary reference for YAIBOS file-based architecture. It runs skills, agent permissions, and memory on existing open CLI harnesses, keeping the files independent of a database.
Criterion 0–5
No terminal
2
Portable skills
3
Own subscription
5
Second brain
4
Permissions & safety
2
Portability
5

Strengths

  • ✓ Agents, skills, and memory live entirely in an open Markdown second brain, viewed and edited with Obsidian.
  • ✓ Per-agent RBAC security contract: declared read-only agents and bounded write zones, with unlisted mutations requiring human-reviewed Git patches.
  • ✓ Context-aware modular installation: detects host tools (Docker, Proxmox, browser) to provision only relevant skills and agents, avoiding context window bloat.
  • ✓ Native Claude Code integration, with portable prompt-generation scripts for other CLI harnesses (OpenCode, Aider, Goose).

Gaps vs YAIBOS

  • – Lacks a zero-install standalone web dashboard for non-technical team members (requires terminal or Obsidian setup).
  • – Permissions model is agent-level rather than multi-user team RBAC: currently designed for a single user/workstation.
  • – Scheduled tasks use versioned registries and timers, but lack 1-click UI execution buttons and duration telemetry.
  • – Early alpha release with documentation currently in French.
Modular Agent Engine & Runtime Grade B+

DeepSeek Harness (dsh + Cordis)

↗

Native Open Harness (Reference Runtime)

An open-source agent harness built on the Cordis plugin engine, with swappable memory, tool, and execution plugins.

Verdict: An architectural reference for a modular open-source agent harness, with community plugins. It currently lacks an interface for non-technical users and multi-user RBAC.
Criterion 0–5
No terminal
2
Portable skills
4
Own subscription
3
Second brain
3
Permissions & safety
1
Portability
5

Strengths

  • ✓ Modular plugin architecture based on the Cordis meta-framework.
  • ✓ Swappable open-source execution, memory (dsh-mnemon), and tool plugins.
  • ✓ Execution telemetry, duration tracking, and audit logs.

Gaps vs YAIBOS

  • – Strictly developer-oriented: requires terminal knowledge and Node.js to deploy.
  • – No native multi-user RBAC or folder permissions.
  • – Requires bridging for consumer subscription auth (ChatGPT/Claude web auth).
Visual Agent Canvas & Self-Hosted Platform Grade B+

Obsidian AI (sup3rus3r/obsidian-ai)

↗

Custom Visual Engine (No Open Harness)

Self-hosted, open-source platform for orchestrating AI agents through a visual drag-and-drop canvas with native MCP support, prompt vault, and team RBAC.

Verdict: Self-hosted visual orchestration with secrets management and support for several LLM providers. Its node canvas is more complex than one-click business skill buttons, and it lacks a native Markdown editor that reads and writes notes.
Criterion 0–5
No terminal
4
Portable skills
4
Own subscription
3
Second brain
3
Permissions & safety
4
Portability
4

Strengths

  • ✓ Drag-and-drop visual canvas for agent teams and DAG execution workflows.
  • ✓ Production security: Fernet secrets vault, AES encryption, JWT auth, and role-based access control.
  • ✓ Native Model Context Protocol (MCP) support and multi-provider model switching without config changes.

Gaps vs YAIBOS

  • – Not built on a standard open harness like DSH or OpenCode: uses a bespoke node-graph runtime, meaning it cannot natively run community harness plugins or shared skill workflows.
  • – Node-and-wire visual canvas still demands workflow logic design rather than simple 1-click skill cards for business staff.
  • – Does not provide an integrated, human-editable Markdown second-brain note vault.
  • – Self-hosting requires Docker or server deployment before non-technical staff can use it.
Custom AI Systems & Automation Studio Grade B

LoopSuit AI

↗

Bespoke Agency Service (No Open Harness)

AI-native product studio and automation agency deploying custom autonomous agents, onboarding pipelines, and bespoke operational workflows for business operators.

Verdict: Custom agency deployments with a focus on operational design and rapid delivery of production-ready MVPs. It does not provide a self-hosted, open-source second-brain operating system.
Criterion 0–5
No terminal
4
Portable skills
4
Own subscription
2
Second brain
2
Permissions & safety
2
Portability
3

Strengths

  • ✓ Custom autonomous agent workflows for lead intake, client onboarding, and operational procedures.
  • ✓ Product design and two-week delivery for operators.
  • ✓ Clients own the deployed automation system.

Gaps vs YAIBOS

  • – Not an open harness and not built on open runtimes like DSH or OpenCode: custom boutique agency automation built on private client infrastructure.
  • – Bespoke agency delivery rather than a standardized, open-source sovereign software harness.
  • – No integrated, bi-directional Markdown second-brain knowledge layer.
  • – Auth and pricing models vary per client setup rather than standardized BYOS session auth.
Visual Harness UI Grade B

OpenDesign / DSHKer

↗

Built on Open Harness (DeepSeek Harness)

A local-first visual desktop interface built on DeepSeek Harness (DSH), designed to make the harness accessible to non-technical users.

Verdict: Uses DSH's modular plugins, execution telemetry, and community updates through a visual desktop layer that does not require terminal setup.
Criterion 0–5
No terminal
4
Portable skills
4
Own subscription
2
Second brain
2
Permissions & safety
1
Portability
4

Strengths

  • ✓ Directly powered by DeepSeek Harness (DSH), inheriting upstream community plugins and runtime improvements.
  • ✓ Zero-install desktop app for non-technical team members.
  • ✓ Visual preview of agent executions and artifacts.

Gaps vs YAIBOS

  • – No integrated team second brain or Markdown editor.
  • – Single-user desktop focus with zero role-based permissions.
  • – Early stage with evolving API stability.
Open Design home screen: prompt box with output types (slide deck, UI mockup, document) and a model picker
Open Design home screen: prompt box with output types (slide deck, UI mockup, document) and a model picker

Screenshots from the project's README (source).

AI Second Brain & Assistant Grade B-

Khoj

↗

Not an Agent Harness (Conversational Search)

Self-hosted AI search and personal assistant that indexes local Markdown notes and documents.

Verdict: Strong on local Markdown second-brain capabilities, but lacks an operational 1-click business skill runner.
Criterion 0–5
No terminal
4
Portable skills
2
Own subscription
2
Second brain
4
Permissions & safety
2
Portability
3

Strengths

  • ✓ Local Markdown indexing and semantic retrieval.
  • ✓ Clean web and desktop interface.
  • ✓ Self-hosted privacy guarantees.

Gaps vs YAIBOS

  • – Not an autonomous agent harness and not built on open harnesses like DSH or OpenCode: custom Python engine focused on personal document retrieval and conversational search.
  • – Oriented toward conversational Q&A rather than running business skills.
  • – No 1-click action cards with telemetry and duration tracking.
  • – Rudimentary team sharing and permission controls.
Knowledge Base + Plugin Ecosystem Grade B-

Obsidian (with Agent & Smart Plugins)

↗

Fragmented Plugins (No Unified Harness)

A local Markdown editor with community agent plugins (Smart Connections, Banners, Local LLMs).

Verdict: Suited to editing a personal second brain. Setup is complex for non-technical staff, and it lacks multi-user RBAC.
Criterion 0–5
No terminal
2
Portable skills
2
Own subscription
2
Second brain
5
Permissions & safety
1
Portability
4

Strengths

  • ✓ Plain Markdown files remain under your control.
  • ✓ A large plugin ecosystem and local graph visualization.
  • ✓ Zero proprietary data format lock-in.

Gaps vs YAIBOS

  • – Lacks a cohesive open harness foundation like DSH or OpenCode: community plugins operate as isolated silos with inconsistent tool permissions and fragmented context.
  • – High onboarding friction for non-technical team members.
  • – Obsidian Sync has zero folder-level RBAC for team permissions.
  • – Agent execution relies on fragmented community plugins rather than a cohesive runtime.
Desktop AI Workspace Grade C+

AnythingLLM

↗

Not an Agent Harness (Document RAG)

All-in-one desktop and enterprise app for chatting with documents and local models.

Verdict: Polished document workspace, but strictly conversational with no concept of business skill execution.
Criterion 0–5
No terminal
5
Portable skills
1
Own subscription
3
Second brain
3
Permissions & safety
3
Portability
2

Strengths

  • ✓ One-click desktop installer with zero technical setup required.
  • ✓ Supports multi-user workspaces and basic permission levels.
  • ✓ Flexible model endpoint configuration.

Gaps vs YAIBOS

  • – Not an agent harness and not built on open runtimes like DSH or OpenCode: custom monolithic Node.js backend designed for document Q&A, lacking autonomous business skill execution.
  • – No 1-click business skill procedures or automated business agent loops.
  • – Data locked in internal vector databases instead of plain Markdown.
  • – Rigid plugin architecture with limited extensibility.
Visual Workflow & LLMOps Grade C

Dify / Flowise

↗

Custom Visual DAG Engine (No Open Harness)

Visual canvas builders for chaining LLMs, tools, and multi-agent workflows into APIs.

Verdict: Visual node workflows suit developers but are complex for non-technical teams. They lack owner-controlled Markdown notes.
Criterion 0–5
No terminal
3
Portable skills
3
Own subscription
2
Second brain
1
Permissions & safety
3
Portability
3

Strengths

  • ✓ Powerful visual logic builder for custom multi-agent chains.
  • ✓ Good team access management in enterprise self-hosted tiers.
  • ✓ Wide support for external API connectors.

Gaps vs YAIBOS

  • – Uses proprietary visual node execution graphs rather than an open harness runtime like DSH or OpenCode, creating workflow lock-in within their specific visual schemas.
  • – Visual node graphs are intimidating for non-technical operators.
  • – Relies on PostgreSQL and cloud vector stores, completely missing sovereign Markdown files.
  • – Heavy infrastructure footprint to self-host.
Self-Hosted Model Interface Grade C+

Open WebUI

↗

Not an Agent Harness (Model Chat UI)

A self-hosted chat interface for Ollama, OpenAI, and compatible endpoints.

Verdict: A self-hosted alternative to ChatGPT, without an operational skill catalog or agent action loops.
Criterion 0–5
No terminal
4
Portable skills
1
Own subscription
3
Second brain
2
Permissions & safety
3
Portability
3

Strengths

  • ✓ Familiar and clean ChatGPT-style user interface.
  • ✓ Good user management and multi-role RBAC in server mode.
  • ✓ Broad model support including local Ollama runners.

Gaps vs YAIBOS

  • – A web chat interface for LLMs rather than an agent harness: not built on DSH or OpenCode, and lacks an autonomous task loop or business skill runner.
  • – Purely conversational: no 1-click execution cards or task duration telemetry.
  • – Lacks a bi-directional Markdown second brain.
  • – Not designed to automate repetitive business processes.
Developer Agent Frameworks Grade D+

CrewAI / AutoGPT / OpenManus

Code Frameworks (Custom Runtimes)

Code-first multi-agent orchestration libraries (CrewAI, AutoGPT, OpenManus) providing programmatic agent harnesses for developers.

Verdict: Support algorithmic experiments through their own custom runtimes. They do not build on modular standards such as DSH or OpenCode, and lack an interface for non-technical users.
Criterion 0–5
No terminal
1
Portable skills
2
Own subscription
1
Second brain
1
Permissions & safety
1
Portability
4

Strengths

  • ✓ Flexible multi-agent role delegation in Python or TypeScript.
  • ✓ Rapidly adopting open standards like Model Context Protocol (MCP).

Gaps vs YAIBOS

  • – Each library invents its own custom programmatic harness rather than converging on modular standards like DSH (Cordis) or terminal standards like OpenCode, resulting in framework churn and developer lock-in.
  • – Zero graphical UI: requires terminal execution and virtual environments.
  • – Metered API use can produce unexpectedly large bills.
  • – No persistent human-readable knowledge layer or team permissions.

Where the gaps are

Common gaps for founder-led small businesses.

1. Tools built for developers

Most frameworks expect users to know Git, Docker, and the terminal. That makes them difficult for non-technical staff to use.

2. Unpredictable API costs

Agent loops can run up metered API costs when team members use them without spending limits. Bring-your-own-subscription (BYOS) access gives each person a way to use their existing AI plan.

3. Context and team access

Context may sit in vector databases that people cannot inspect, or in personal note apps without team permissions or agent runners.

4. Maintaining a custom runtime

A custom agent runtime needs its own tool drivers, plugins, and fixes. Building on an open-source harness such as DeepSeek Harness or OpenCode gives projects access to shared plugins, adapters, and security patches.

Weekly tech watch

The Sovereign AI & Harness Radar

One concise email each Wednesday on agent harnesses, Markdown second brains, and practical business workflows. Written by Samuel Michelot, no sponsor fluff.

Weekly · 5-minute read · 1-click unsubscribe

Contact

Questions about YAIBOS, the Bootcamp, or a tool for the scorecard?

Leave an async video, voice note, or short text message for Samuel. No meeting needed unless you want to book a call.

Send a message ↗ About Samuel

A few cookies?

With your permission, we use cookies to understand visits, improve the site and show you relevant advertising.

Privacy