Skip to main content
Get StartedOverviewPricingProofsIntegrations
Plugs Into Modern AI Workflows

One environment variable. The tools you already use.

Open the app and Transmute wires up your AI tools itself. Hermes with any provider, Claude Code and Claude CLI, Codex, OpenAI, Cursor. No env vars, no SDK, no per-tool setup. More on the way.

Book a consultation
How Transmute works
Provider Matrix

One app. The tools you already use.

Transmute configures your AI tools itself. No env vars, no proxy setup: open the app and your covered tools are protected.

Tool
Coverage
Setup
Hermes
Kimi, DeepSeek, OpenAI, Venice, any provider configured in Hermes
Automatic, one toggle covers every provider
Anthropic
Claude Code, Claude CLI, Claude Desktop
Automatic, no config edits
OpenAI
Codex, ChatGPT desktop, OpenAI SDK
Automatic, no config edits
Cursor
Cursor desktop
Automatic, no config edits
Coming soon
Windsurf, local models, more on the way
Missing your tool? Tell us at /feedback

Open the app · that's the entire integration

MCP & Extensibility

Transmute plugs into your existing AI workflow.

If you use AI coding tools with MCP servers, Transmute sits transparently in the egress path, no MCP config changes, no tool modifications. Every tool call, every file read, every API request flows through Transmute's redaction engine automatically.

No MCP config changes

Transmute sits transparently in the egress path between your AI tools and the API. Your MCP servers, tools, and configurations remain untouched.

All tools protected

Whether your AI tools call filesystem tools, web fetch, or your custom MCP servers, every request transits through Transmute's redaction engine.

Works with your MCP hosts

The tools Transmute configures keep their MCP servers, tools, and custom setup untouched. Protection rides between the tool and the provider, not inside your workflow.

How it works with your AI tools

Your AI tools read tools from your MCP config and call their provider APIs. Transmute wires itself in: automatic, no config edits and every request, whether it's a prompt, a tool result, or file content, passes through Transmute before reaching the provider. Secrets are tokenized. PII is redacted. Responses are rehydrated. Your tools never know Transmute is there.

Zero-Code Integration

One environment variable. No SDK. No import.

Every other AI security tool requires you to install a library, import it in your code, and wrap every LLM call. Transmute requires none of that. It sits on the wire, your code doesn't even know it's there.

No SDK

No pip install, no npm package, no library dependency. Transmute is a standalone Go binary that runs on your infrastructure.

No Import

No import statements. No middleware registration. No client wrapping. Your application code stays exactly as it is.

No Per-Tool Config

Claude Code and Claude CLI, Codex, OpenAI, Hermes with any provider, Cursor, all protected automatically. No per-tool configuration needed.

Infrastructure-Level

Deploy Transmute once on your network. Every AI call from every developer and every tool is protected, automatically.

One variable. Ten minutes. Protected.

Your team keeps using the tools they know. Transmute wires them up itself: Claude Code and Claude CLI, Codex, OpenAI, Hermes with any provider, Cursor. Security handled transparently.

Fixed-price engagement · Source code at handoff · No subscription

FAQ

Transmute Integrations FAQ

How many environment variables do I need to configure?

None. Open the app and Transmute wires up your covered tools itself. No env vars, no SDK changes, no per-tool setup.

Which tools does Transmute cover today?

Hermes with any configured provider (Kimi, DeepSeek, OpenAI, Venice and more), Claude Code and Claude CLI, Claude Desktop, Codex and OpenAI, and Cursor. If your provider runs through Hermes, one toggle covers it.

My tool isn't on the list. Now what?

Coverage is growing. Tell us what you use at /feedback and it shapes what ships next.

Can I use Transmute with local models like Ollama or LM Studio?

Not yet. Local model support is on the roadmap. If that is your setup, tell us at /feedback so we prioritize it.

Does Transmute support streaming responses?

Yes. Tokenization and rehydration work on streaming responses in real time. Transmute buffers only enough to detect patterns, then streams the rest.

Does Transmute add latency that my users will notice?

Transmute runs locally on your machine. Overhead is a small fraction of a typical AI request, which takes hundreds of milliseconds to seconds. Your workflow won't notice it exists.