CorvinOS – self-hosted OS for AI agents, compliance built into the runtime

shumway1 pts0 comments

CorvinOS — The Operating System for AI Organizations

Apache-2.0 · The self-hosted agentic OS

The agentic OS<br>you actually own.<br>EU-compliant by design.

A self-hosted operating system for AI agents: it runs the engines, personas, workflows and runtime-forged tools, meets your users on every messenger, drives a real browser, and keeps a hash-chained audit of it all — with compliance built into the architecture, not bolted on.

Star on GitHub

Quick Start →

Messaging bridges

Engines detected

Compliance frameworks

0%

Self-hosted

The command center<br>The chat runs the whole OS

The chat isn't a demo window — it's the shell. Personas, engines, workflows, the Forge, RAG, agentic compute and the A2A mesh are all reachable from one prompt. And you can drive it end‑to‑end by voice: speak a request, CorvinOS transcribes it, routes it, does the work, and speaks the answer back — tuned to how you listen. And you don't even need the console open: every messaging bridge is a full control surface, so you can run the whole OS straight from a Telegram, WhatsApp or Signal thread.

Voice on

Voice in · voice out<br>Run it hands‑free

Hit the mic and talk. Speech is transcribed locally by default — the audio is deleted the moment it returns, and only metadata ever touches the audit chain.

🎙️

Speak &ldquo;Rank Q2 cohorts by retention.&rdquo; — captured from any bridge.

Transcribe Local Whisper by default, OpenAI as fallback. Runs before the engine even wakes.

Route A persona and engine are picked for the turn — your overrides always win.

Act One turn can reach every layer: Forge, workflows, RAG, agentic compute, A2A.

🔊

Speak back Answer is spoken through a listener‑tuned voice — jargon and depth to taste.

One prompt reaches every layer

🎭

Personas<br>Many minds, one runtime — routed per turn.

⚙️

Engines<br>Claude, Codex, OpenCode & local models.

🔀

Workflows<br>Multi-step AWP pipelines, on demand or scheduled.

🔨

Forge<br>Schema-bound tools & skills, built at runtime.

📚

RAG<br>Grounded answers over your own documents.

🧮

Agentic Compute<br>Sweeps & tuning without spending tokens.

🔗

A2A mesh<br>Signed task envelopes across teams.

🛡️

Audit<br>Every step on a hash-chained spine.

Regulatory compliance<br>Built in, not bolted on.

Every compliance mechanism is a structural design constraint. There is no "compliance mode" you can accidentally leave off.

EU AI Act Art. 50

Bot Disclosure

One-time AI-nature disclosure per user, structurally locked. Cannot be disabled via configuration.

GDPR Art. 6 & 7

Consent Gate

Deny-by-default consent for transcript sharing. Per-user, TTL-capped, re-validated at consume time.

GDPR Art. 30 & 32

Hash-Chained Audit

Every event appends to a SHA-256-linked chain. Tampering invalidates it. Offline-verifiable.

EU AI Act Art. 14

Data Residency

Compliance-zone routing and egress lockdown structurally prevent data from leaving the permitted zone.

EU AI Act 2026<br>GDPR<br>ISO/IEC 42001<br>NIST AI RMF

Agentic Compute<br>Compute that adapts<br>to any problem

That's Agentic Compute : the worker owns the loop, the model owns the framing. The agent says what to optimise and when to stop; a sandboxed worker picks the strategy that fits the problem and turns the crank — from a quick tune to a Bayesian search over an 8 GB dataset, and never a raw byte in the context window.

01

Frame it The model submits one job — what to optimise, the parameter space, and the stopping rule.

02

Run it A sandboxed worker evaluates combinations in parallel and streams Top-K progress back.

03

Read it Three model calls total — submit, poll, read. Zero tokens spent while the loop turns.

3 model calls / sweep<br>up to 16 parallel<br>SHA-256 audited

compute_run<br>bayesian · GP + EI

sweep · learning_rate × n_estimators · 4 parallel

w0

w1

w2

w3

4/100<br>iterations

↓ 0.900<br>best loss

● sha-256

N iterations run in the worker — the model is idle until the result returns.

grid

Exhaustive coverage

Evaluates every combination in the grid. Pre-generated at submit — deterministic and fully reproducible.

random

Broad sampling

Uniform samples per batch from continuous ranges. One seed per run, stored for reproducibility.

bayesian

Fewest evaluations

A Gaussian-Process surrogate picks the highest Expected-Improvement points — finds a good region in the fewest runs.

Recursive delegation · the ACS run<br>It keeps working until the answer is good enough

A manager engine plans the task, delegates pieces to parallel worker runs, scores every result, and iterates toward a loss target. The point of the recursion is adaptation : where a capability is missing, a worker forges the tool or skill it needs at runtime — so the same flow can tune a model, run a backtest, or analyse an 8 GB dataset straight from a prompt.

★ MANAGER · claude-sonnet-4-6

loss — · idle

ITER 1<br>queued<br>loss 0.82

W-A★ sub-mgr↳ spawnsSW-B1 · hermesSW-B2 · hermesW-C ⚒ forge.create_tool()

ITER 2<br>queued<br>loss 0.51

W-DW-EW-F ✦ skill.create()

ITER 3<br>queued<br>loss...

compliance agentic from compute worker model

Related Articles