Products

IO is not a single-model chat wrapper. It is a private AI provider — an inference layer reachable from web, CLI, MCP, SDKs, and messaging relays. Every surface inherits the same three properties: open-weight multi-model inference, redaction before the model observes input, and a signed receipt on every response.

IO SDK

Embed the provider into your own stack. Rust, Python, TypeScript, Go — five lines to inference.

from io_sdk import IO
io = IO()
r = io.completion("Explain ZK proofs",
                  model="claude",
                  ttl=300, redact=True)
print(r.text, r.receipt.verify())

Coming Soon

Extending the same primitives to new surfaces.

IO Room

E2E encrypted collaborative rooms with private AI sidebar

IO Canvas

Infinite whiteboard with AI co-creator

IO Files

Document analysis with field-level redaction

IO Memory

Client-side encrypted agent memory

IO Agents

Autonomous agents with receipt-audited steps

IO Relay

Telegram, WhatsApp, Signal, Discord, SMS bridges