> For the complete documentation index, see [llms.txt](https://seekspeed.gitbook.io/seekspeed-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://seekspeed.gitbook.io/seekspeed-docs/getting-started/what-is-seekspeed.md).

# What is SeekSpeed Terminal

SeekSpeed Terminal is a self-contained web application that sits between your agent code and your inference backend. It does four things, in order:

1. **Captures** real performance signals from any OpenAI-compatible endpoint.
2. **Quantifies** them with proper statistics (means, p50/p95/p99, Welch's *t*-test).
3. **Prescribes** rule-based optimizations with expected impact and difficulty scores.
4. **Verifies** that an applied change is actually faster, not just different.

For self-hosted stacks, it adds a fifth axis — **speculative decoding profiling** via the Spec Lab, with native support for the DeepSpec reference workers and DSpark draft/target pairings.

## The product surface

| Surface          | Path                                  | Purpose                                                                           |
| ---------------- | ------------------------------------- | --------------------------------------------------------------------------------- |
| Marketing site   | `/`, `/features`, `/docs`, `/pricing` | Public-facing pages.                                                              |
| Onboarding       | `/app/onboarding`                     | Guided setup checklist with optional demo seed.                                   |
| Connectors       | `/app/connectors`                     | Manage OpenAI-compatible endpoints with provider presets.                         |
| Agents           | `/app/agents`                         | CRUD for agent profiles (prompt, model, tools, memory, budget).                   |
| Benchmarks       | `/app/benchmarks`                     | Define prompt sets, run multi-iteration benchmarks with concurrency control.      |
| Optimizations    | `/app/optimizations`                  | Browse recommendations, apply variants, re-run, accept/reject.                    |
| Spec Lab         | `/app/spec-lab`                       | Speculative-decoding orchestration for self-hosted endpoints.                     |
| Regression Guard | `/app/guard`                          | Pin baselines, schedule benchmarks, alert on p95 / cost / error-rate regressions. |
| Reports          | `/app/reports`                        | Snapshot runs, compare A/B, export JSON / CSV / HTML.                             |

## What's running underneath

* **TanStack Start v1** on Vite 7, React 19, TypeScript strict mode.
* **Tailwind v4** with a CSS-first token system in `src/styles.css`.
* **Recharts** for latency distributions, breakeven curves, and concurrency sweeps.
* **TanStack server functions** for every backend operation — real HTTP calls, no mocks.
* **Postgres** with row-level security on every table, scoped to the workspace owner.
* **DeepSpec adapter layer** for vLLM / TGI / llama.cpp metric ingestion.

The rest of this book walks through each surface in depth, with the code that powers it.

Continue to [Installation →](/seekspeed-docs/getting-started/installation.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://seekspeed.gitbook.io/seekspeed-docs/getting-started/what-is-seekspeed.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.