Deep dive

Go deeper.

Comparison, AI PC rationale, tradeoffs, costs, and deployment paths for the local compounding engine between your brain and your AI clients.

Core thesis

The AI is replaceable. The brain should compound.

Augur is a local harness layer, not an LLM wrapper, and it does not require an Augur API key. Claude, Codex, Gemini, Cursor, and Ollama remain the native thinking engines you already use. Augur is the local MCP and compounding layer that lets those engines operate the same brain and write useful outcomes back into durable files.

1

Bring your own AI client

Your existing subscriptions and local models provide reasoning. Augur gives them one persistent brain to work against.

2

Operate through local MCP

The adapter is exposed locally: memory, skills, files, workflows, approvals, and tools stay inspectable instead of disappearing into a cloud wrapper.

3

Keep the second brain

Switch models or remove Augur without losing the notes, wiki, memory, prompts, skills, workflows, and source cards that make the system yours.

The principles

Five core values.

1TrustRead every file your AI reads. No black boxes. Privacy by architecture, not by policy.
2FreedomClaude today, Gemini tomorrow, Ollama offline — same brain. No vendor lock-in or pricing dependency.
3PaceGrow your second brain at your speed. Every skill is readable, every decision documented. Understand before you depend.
4SovereigntyNo server, no account. Your second brain survives any vendor shutdown.
5Future-proofMarkdown, YAML, Agent Skills, and MCP boundaries are readable in 10 years, with or without Augur.
Two modes

Choose your path.

Operation mode

Install community skill packs.
Fill them with your data.
Get AI-assisted immediately.
Technical level
Same as using ChatGPT or Claude.

Dev mode

Build your own skills.
Customize everything.
Shape the system to your life.
Technical level
Domain knowledge + taste + AI fluency. No coding required.

Most people start in Operation mode. Some grow into Dev mode. Both are valid — the system meets you where you are.

Honest tradeoffs

Augur is not magic.

1

You will learn more

Not coding — but how your system works. YAML files. Markdown. How skills connect. You build trust because you can see exactly what your AI knows.

2

You will stay in the loop

Augur keeps you in decisions that matter. More time, but you remain the architect.

3

You will take responsibility

When something breaks, you fix it. Uncomfortable — and how you grow.

Why the PC

Your second brain needs the edge.

People sync files to their PC even when they have cloud storage — because important files only on the cloud feels risky. Your second brain is higher stakes than files.

Storage

The persistent home for cross-session memory, skills, workflows, and business logic. No cloud database, no sync latency — your second brain lives on flash storage you control.

CPU

The orchestrator and integration manager. Connects CLIs to AI providers, runs the MCP server, manages the daemon, spawns processes. The CPU makes the PC the integration hub.

GPU

Full offline reasoning via quantized local models. When you need capability without internet, the GPU keeps Augur fully functional in airplane mode.

NPU

Real-time, privacy-critical inference: speech-to-text via Whisper, OCR via Tesseract. These tasks need low latency and must never leave the device.

For who

Who is Augur for?

For individuals

  • Use five AI tools that don't know each other
  • Tired of being the router between vendors
  • Want a second brain you own, not subscribe to
  • Value privacy — personal data stays on your machine

For organizations

  • Bottom-up AI transformation — no IT bottleneck
  • Deploy through CLIs and IDEs employees already use
  • Project brains that retain institutional knowledge
  • From IT's perspective: local scripts and text files
The economics

The real cost of rented AI.

AspectCloud-only AIAugur
Your data & memoryStored on provider's serversOn your disk — always
Workflows & skillsLocked to one platformLive repo skills and private vault drafts (open SKILL.md format)
LLM providerSingle vendor lock-inBring your own — Claude, GPT, Ollama, any
Switch providersLose everythingKeep all data, swap the AI
PrivacyProvider's terms of serviceYour files never leave your machine
CustomizationLimited to provider UILive repo skills, private vault drafts, community packs, full dashboard
Overnight opsCosts money per API callAuto-commands run free on idle hardware
Offline modeNo internet = no AIFull airplane mode with local LLM via Ollama

Augur is the persistent layer. The AI is replaceable.

Ready to start?

Start on the homepage for early access, or open the public Augur OS repository for the philosophy, architecture, and implementation details.