> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tinfoil.sh/llms.txt
> Use this file to discover all available pages before exploring further.
# Using coding agents with Tinfoil hosted models
> Using Tinfoil private inference with any OpenAI-compatible coding agent and connection-time attestation verification.
Most coding agents (Cline, Factory Droid, OpenCode, Hermes, Continue, Aider…) talk to a configurable OpenAI-compatible base URL.
That's all Tinfoil needs to slot in.
However, to ensure each connection is attested and the privacy is verified by your client, you need to run a Tinfoil proxy.
In this tutorial we explain how to set up a local proxy that automatically verifies the attestation for all inference requests issued to Tinfoil.
## The recommended setup
Install the [Tinfoil Proxy menu-bar app](/local-proxy/app) or the [standalone CLI binary](/local-proxy/cli). Either way you get the same `http://127.0.0.1:3301/v1` endpoint with identical attestation; pick the menu-bar app for desktop use and the CLI for scripts, CI, or headless servers.
Configure your coding agent with:
| Setting | Value |
| -------- | -------------------------------------------------------------------------- |
| Base URL | `http://127.0.0.1:3301/v1` |
| API key | Your Tinfoil API key from the [Tinfoil Dashboard](https://dash.tinfoil.sh) |
| Model | A model ID from the [chat model catalog](/models/chat), e.g. `kimi-k2-6` |
With the menu-bar app, open the Tinfoil popup and confirm the lock is green. With the CLI, watch the logs for the verification success line on startup.
### The general case
If your tool or harness supports OpenAI compatible inference APIs and exposes the ability to set a base URL, you should be able to configure it to work with the values in the table above.
**Verification Note:** OpenAI-compatible clients don't perform connection-time attestation themselves. With the [Tinfoil Proxy menu-bar app](/local-proxy/app) or the [CLI proxy binary](/local-proxy/cli) in the loop, every request gets a verified connection to a Tinfoil secure enclave. Without either, your traffic still benefits from audit-time verification through Tinfoil's [attestation transparency log](/verification/verification-in-tinfoil#in-band-vs-out-of-band-verification).
However, we strongly recommend using the proxy.
## Cline
[Cline](https://cline.bot) is a VS Code coding agent with a built-in [OpenAI Compatible provider](https://docs.cline.bot/provider-config/openai-compatible). It is a good fallback when you want a simple settings UI for a custom base URL.
Open VS Code, search for **Cline** in the Extensions sidebar, install it, and reload when prompted.
Open Cline settings, choose **OpenAI Compatible** as the API Provider, and enter:
| Setting | Value |
| ------------ | ------------------------------------------------------------------- |
| **Base URL** | `http://127.0.0.1:3301/v1` |
| **API Key** | Your Tinfoil API key |
| **Model ID** | `glm-5-2` or another ID from the [chat model catalog](/models/chat) |
Use the `/v1` base URL, not the full `/chat/completions` endpoint.
Click **Verify** if Cline offers it, then start a task. Requests for that model route through the local proxy and into the enclave.
### Privacy
With Tinfoil configured as Cline's OpenAI-compatible provider, inference requests for that model are pointed at the local proxy. Cline's extension runs in VS Code; review Cline's [privacy notice](https://cline.bot/privacy) for any product analytics or account features you enable.
## Kilo Code
[Kilo Code](https://kilo.ai) is an open-source coding agent for VS Code, JetBrains, the CLI, and cloud workflows. Its [OpenAI-compatible provider docs](https://kilo.ai/docs/ai-providers/openai-compatible) support custom base URLs and API keys.
Install **Kilo Code** from the VS Code Marketplace.
Open the Kilo Code sidebar, click the Kilo settings gear, then open the provider settings. Do not use VS Code's global Settings search (`@ext:kilocode.kilo-code`); Kilo keeps provider setup inside its own webview. Under **Custom provider**, click **Connect** and configure:
| Setting | Value |
| ----------------- | --------------------------------------------------------------------- |
| **Provider type** | `OpenAI Compatible` |
| **Display name** | `Tinfoil` |
| **Base URL** | `http://127.0.0.1:3301/v1` |
| **API Key** | Your Tinfoil API key |
| **Model** | `kimi-k2-6` or another ID from the [chat model catalog](/models/chat) |
Use the `/v1` base URL, not the full `/chat/completions` endpoint. If **Custom provider** is not visible, update the Kilo Code extension.
Select the Tinfoil model in Kilo Code and start a task. Requests for that model route through the local proxy and into the enclave.
### Privacy
With Tinfoil configured as an OpenAI-compatible provider, inference requests for that model are pointed at the local proxy. Kilo may still use its own services for account, product, or hosted-model features; see Kilo's [privacy policy](https://kilo.ai/privacy).
## OpenCode
[OpenCode](https://opencode.ai) is a terminal-based coding agent that talks to any provider exposed via the AI SDK. It plugs into Tinfoil through the `@ai-sdk/openai-compatible` adapter — see OpenCode's [Providers](https://opencode.ai/docs/providers/) and [Config](https://opencode.ai/docs/config/) docs for the full schema.
Add Tinfoil as a custom provider in `opencode.json` (project root or `~/.config/opencode/opencode.json`):
```json theme={"dark"}
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"tinfoil": {
"npm": "@ai-sdk/openai-compatible",
"name": "Tinfoil",
"options": {
"baseURL": "http://127.0.0.1:3301/v1",
"apiKey": "tk_xxxx"
},
"models": {
"kimi-k2-6": {
"name": "Kimi K2.6",
"limit": { "context": 200000, "output": 65536 }
},
"gemma4-31b": {
"name": "Gemma 4 31B",
"limit": { "context": 128000, "output": 32768 }
}
}
}
}
}
```
Paste your Tinfoil API key directly into the `apiKey` field, then pick the Tinfoil provider in OpenCode's `/models` selector and start coding.
### Privacy
OpenCode is open-source and runs locally on your machine. Its [Enterprise docs](https://opencode.ai/docs/enterprise/) state:
> OpenCode does not store your code or context data. All processing happens locally or through direct API calls to your AI provider.
With the Tinfoil provider configured, those direct calls go to the local proxy and into the enclave. The exception OpenCode flags is the optional `/share` feature, which uploads the active conversation to opencode.ai's CDN — leave it off (or set `"share": "disabled"` in `opencode.json`) to keep everything on-device.
## Factory Droid
[Factory Droid](https://factory.ai) is a terminal-native coding agent that supports custom OpenAI-compatible providers through its [Bring Your Own Key](https://docs.factory.ai/cli/byok/overview) configuration.
Follow the [Droid CLI quickstart](https://docs.factory.ai/cli/getting-started/quickstart) to install `droid` and sign in.
Add a `customModels` entry to `~/.factory/settings.json`:
```json theme={"dark"}
{
"customModels": [
{
"model": "kimi-k2-6",
"displayName": "Kimi K2.6 (Tinfoil)",
"baseUrl": "http://127.0.0.1:3301/v1",
"apiKey": "tk_xxxx",
"provider": "generic-chat-completion-api",
"maxOutputTokens": 65536
}
]
}
```
Paste your Tinfoil API key directly into the `apiKey` field. The `generic-chat-completion-api` provider speaks OpenAI Chat Completions, which is what `tinfoil-proxy` exposes on `:3301/v1`. Duplicate the block to add more models from the [chat model catalog](/models/chat) — set `model` to the model ID (e.g. `gemma4-31b`, `glm-5-2`) and pick a friendly `displayName`.
Open the Droid CLI and run `/model`. Your Tinfoil entries appear under **Custom models** — pick one and start prompting. Switch back at any time with `/model`.
### Privacy
With a [custom model](https://docs.factory.ai/cli/byok/overview) pointing at the local Tinfoil proxy, Droid sends LLM traffic from your machine to the Tinfoil enclave. Factory's [Privacy, Data Flows & Governance](https://docs.factory.ai/enterprise/privacy-and-data-flows) docs cover customer-configured endpoints:
> LLM traffic is handled entirely by your providers and gateways; Factory does not see it.
The [BYOK Overview](https://docs.factory.ai/cli/byok/overview) adds:
> Your API keys remain local and are not uploaded to Factory servers.
The Droid CLI still talks to Factory's cloud for orchestration, and may emit [OpenTelemetry](https://docs.factory.ai/enterprise/privacy-and-data-flows#telemetry-and-analytics) signals unless you point them at your own collector or disable analytics.
## Hermes Agent
[Hermes Agent](https://github.com/NousResearch/hermes-agent) is a self-improving AI assistant from [Nous Research](https://nousresearch.com). See Hermes' [`hermes model` reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands#hermes-model) for the full provider wizard.
[Install Hermes](https://hermes-agent.nousresearch.com/docs/getting-started/installation/), then run the interactive model picker from your terminal (not from inside a Hermes chat — `/model` can only switch between providers you've already configured):
```bash theme={"dark"}
hermes model
```
Highlight **Custom endpoint** and press Enter. Provide:
| Setting | Value |
| -------------- | ---------------------------------------------------------------------------------------- |
| **Base URL** | `http://127.0.0.1:3301/v1` |
| **API key** | Your Tinfoil API key from the [Tinfoil Dashboard](https://dash.tinfoil.sh) |
| **Model name** | A model ID like `kimi-k2-6` or `gemma4-31b` (see the [chat model catalog](/models/chat)) |
```bash theme={"dark"}
Enter base URL: http://127.0.0.1:3301/v1
Enter API key (or press Enter to skip):
Enter model name: kimi-k2-6
Configuration saved to ~/.hermes/config.yaml
```
Confirm everything is wired up:
```bash theme={"dark"}
$ hermes doctor
✓ Config file exists
✓ Dependencies installed
✓ API connection successful
✓ Model kimi-k2-6 is accessible
```
### Privacy
Hermes is MIT-licensed and runs entirely on your machine. The Hermes [FAQ](https://hermes-agent.nousresearch.com/docs/reference/faq#is-my-data-sent-anywhere) states:
> API calls go only to the LLM provider you configure (e.g., OpenRouter, your local Ollama instance). Hermes Agent does not collect telemetry, usage data, or analytics. Your conversations, memory, and skills are stored locally in `~/.hermes/`.
With the custom endpoint pointed at the Tinfoil proxy, requests go from Hermes to the local proxy and into the enclave.