Claude, OpenAI, Gemini, open models — choose what fits, move between them without losing your thread, and keep your workspace yours.
Anthropic Messages API with real token streaming. Requires an Anthropic API key.
Real APIs, real keys, no demo mode
Real provider logos, real endpoints, real streaming. Pick a model, paste a key, and the same conversation carries across labs.
No account walls, no model lock-in, no fake answers. A sharp interface that gets out of the way of the work.
Send a prompt, switch models, and keep the same context without losing track of which provider answered. Replies stay labeled by model.
Native tool calling with a real loop: the model asks, Eltes executes locally and feeds the result back — with timing for every step.
Each provider key is stored locally and attached at request time. Requests go directly to the provider by default; you may opt into your own Vercel/local proxy. Provider billing remains with the provider.
Threads, titles and pins live in local storage. Search them from the palette, export them as Markdown, delete them in one click.
Every reply records time to first token, total latency, input and output tokens, and tokens per second straight from the provider's usage payload.
401, 429, CORS and offline each get a specific explanation and a retry that keeps your prompt. No silent fallbacks, no invented replies.
Eltes runs a real tool loop through your provider: the model requests a tool, the browser executes it, the result goes back into the conversation. Every call is timed and visible.
For example: calculate, read the clock, or search chat history.
No shell access. No arbitrary terminal commands. The result is shown to you.
When enabled, the provider receives the tool result to finish its answer.
Pick the model, choose how the request is sent, and keep control of your local workspace.
| Capability | Eltes | What that means |
|---|---|---|
| Model choice | 36 catalogue entries | Hosted providers plus your own OpenAI-compatible endpoint. |
| Provider access | Bring your own key | Direct from the browser by default; optional trusted proxy. |
| Conversation continuity | Switch mid-thread | Choose a different model without discarding the chat. |
| History | Local by default | Export or clear it from this browser at any time. |
| No-key option | Eltes CAI | A small, bounded on-device helper—not a frontier LLM. |
| Agent tools | Visible and local | Calculator, clock, and chat search; no shell access. |
| Usage visibility | Latency and tokens | Metrics depend on what each provider reports. |
| Hosted billing | Provider-controlled | Provider pricing and account limits still apply. |
The workspace is free. Hosted model replies require your provider API key and may be billed by that provider. CAI runs locally at no per-token cost. No Eltes hosted plan or free hosted credits are available yet.
Connect your provider key for real streamed replies. Eltes checks for a saved key before sending; without one, use CAI locally for free.
Hosted keys, one bill and no setup. The same workspace, without pasting anything.
For teams that want centralised keys, audit trails and SSO.
Pricing is a placeholder while the beta runs. Nothing is charged, and no card is ever requested. Read the pricing notes.
Eltes connects OpenAI, Anthropic and DeepSeek directly. Sign up with the provider that already pays for your models, or keep a local profile with no account at all. The profile lives in this browser. Hosted model requests may optionally use a Vercel/local proxy that you configure; the profile itself remains in this browser.
No password and no email is sent. Provider keys stay in this browser. How accounts work
The app is a static site. The Windows launcher serves the files locally and opens your browser — no installer, no registry, no admin rights, no background service. An optional Node/Vercel backend supports key testing and proxying.
Unzip anywhere and double-click eltes.bat. It finds Python or Node,
serves the folder on 127.0.0.1:4173 and opens the workspace.
--shortcutClone the repository and run npm install && npm start to serve the site with the optional local API. A static server such as Python works too, but does not run key checks or the proxy.
npm startEltes ships a web manifest. Use your browser’s Install or Add to Home Screen action to get a standalone window with the green-cloud icon.
Open the workspaceThe launcher is a reviewable text file — read it before you run it. It binds to localhost and only serves files from the folder you unzipped; it does not run the optional API backend.
Every hosted answer comes from a live provider you connected. Or start with Eltes CAI and get a real on-device answer before you add a key — no simulated replies, no fake latency.