Products · app · API · engine · extension
The Nyquest App is the primary product. Around it: a public REST API for developers, a self-hosted engine for air-gapped deployments, and a browser extension. Pick what fits how you work.
01 · Primary product · app.nyquest.ai Live
A full AI workspace. Talk to models from every major provider through one interface. Smart routing across tiers, model pinning, web grounding, persistent memory with vector recall, agent mode, artifacts (14 file types), audio + image generation, and ten distinct visual chassis — all in one place.
Free has access to BYOK plus whichever models are currently no-cost in the catalog. Pro unlocks every model — Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5, GPT-6 Astra · Astra (batch) · Astra Pro, and the rest. Circuit breakers fail over between tiers automatically; you always know which model handled which request.
Lock any conversation to a specific model. Your pinned model handles every message in that thread — no routing surprises, no model switching mid-conversation.
Bring your own API keys for OpenAI, Anthropic, Google, xAI. Keys are AES-256-GCM encrypted at rest and used for direct provider calls. Your rates, your billing.
Live web search and full-page fetch injected into context before the model responds. No Tavily key required — built in. Responses cite the URLs they used.
Conversations persist. A separate memory system extracts facts across sessions, sanitizes PII, and recalls relevant ones via vector search at chat time. Confidence-scored.
Multi-step planner that decomposes a request, runs tools (search, fetch, artifact creation, memory query), and streams steps over SSE. Per-run guardrails on cost, time, and steps.
02 · Create
Type a prompt, get an image. Ask for speech, get audio. Nyquest detects creative intent and routes to the right model automatically.
Describe what you want. Nyquest detects image intent and routes automatically. Images appear inline in your conversation and saved to your gallery.
Generate natural-sounding speech from text. Multiple voices. Long-form inputs are auto-chunked. Audio files saved to your account and playable in the browser.
Dedicated Image Studio and Audio Studio for focused media work. Choose models, adjust settings, and manage generated files in one place.
03 · Splicer — verify Premium
The Splicer fans a single prompt out to multiple frontier models in parallel, streams each response as it lands, then runs a consensus engine across them: an agreement score, the dominant position, a synthesized answer, and — just as important — exactly where the models diverge.
Every run comes with receipts: each model's full response, its cost, and its latency, side by side. For high-stakes answers — legal reading, medical literature, architecture decisions — one model's confident voice isn't evidence. Agreement across rivals is.
The number of models per splice scales with your plan. Splicer surfaces a higher-confidence, consensus-backed answer — it does not guarantee correctness, and it shows you the dissent instead of hiding it.
Explore Splicer in depth →Consensus engine · illustrative run
Synthesized consensus + full per-model responses, costs and latencies below every run.
04 · Artifacts
Drop a file into a conversation. Nyquest processes it automatically — extracts text, structures data, generates previews — and injects it into the model's context. 14 file types, 50+ extensions accepted. Per-user 100 MB media cap.
Text extracted automatically. Full document content injected as context.
Word, Excel, PowerPoint processed. Tables and structure preserved.
Source files in dozens of languages. Indexed and made available verbatim to the model.
Parsed and structured. Schema detected. Key-value data available to models.
Tabular data parsed. Log files indexed. Plain text included directly.
Passed to vision-capable models. Used for analysis, OCR, and visual reasoning.
Audio files transcribed and analyzed. Generated TTS clips saved to your account.
Network captures parsed. Packets, protocols, IPs, DNS, TLS, HTTP extracted.
Plus archives, structured data formats, and more. Async processing for large files.
05 · Models + routing
418 models available through a searchable selector. Pin a specific model or let the dispatcher route through tiered defaults. Bring your own API keys for direct provider billing.
T1 handles everyday work fast. T2 brings frontier-class models for Pro. T3 takes on deep reasoning and heavy workloads. Circuit breakers fail over between tiers automatically — every routing decision is visible and overrideable.
Lock a conversation to a specific model. GPT-6 Astra, Claude Fable 5.1 (batch), Gemini 3.8 Flash (batch), Grok 4.6 — whatever you want. The pinned model handles every message.
Bring your own API keys. Requests go directly to the provider under your account. Your rates, your billing. Keys encrypted with AES-256-GCM.
Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5
GPT-6 Astra · Astra (batch) · Astra Pro
Gemini 3.8 Flash (batch) · 3.8 Flash · 3.7 Flash
Grok 4.6 · 4.5 · Build 0.1
via multi-provider routing
06 · Web grounding
Nyquest searches the web and fetches actual page content. Results are injected directly into model context before the response is generated.
Runs a web search, then fetches full page content. Sandboxed, content-type gated, size-capped. Sources logged for provenance.
Ask about today's news, current prices, recent events. Responses grounded in live data, not stale training data.
Web grounding is built into the platform. No Tavily key. No SerpAPI subscription. Toggle on and go.
07 · Memory
Full conversation history stored. A separate memory system extracts facts, sanitizes PII, scores them by confidence, and recalls the relevant ones via vector search at chat time.
Every conversation is stored. Auto-generated titles. Pick up where you left off. Soft-deleteable, searchable, organizable into projects.
Embedding-indexed fact store. At chat time, your message is embedded and the top-K relevant facts are vector-searched and injected into context.
Newer and more-corroborated facts rank higher. Stale facts decay. PII and credential-shaped numerics are scrubbed before storage.
08 · Agents
Hand off a goal — not just a prompt. Agent mode plans, executes tools, and reports back. Steps stream live, every action is auditable, and per-run guardrails cap cost and time.
The planner decomposes your goal into steps. The runtime executes each step, with the tool registry deciding what tools (search, fetch, artifact creation, memory query) the agent can call.
Watch each step happen in real time. The agent timeline shows tool calls, intermediate reasoning, and partial results as they arrive — no polling, no surprises.
Every run has step, time, and cost caps. You can stop a run at any moment. Per-run state and per-step records are persisted — fully auditable.
Agent mode is in beta. Available on every plan.
09 · Analytics
Every request is logged. Every routing decision is visible. You always know which model handled a request, how many tokens it used, and what it cost.
Per-request cost, tokens in/out, model used, latency. Broken down by day, by model, by conversation.
See which tier was selected, which model actually served the request, and why. No black-box decisions.
Full transaction history. Wallet balance, charges, top-ups. Every dollar accounted for.
10 · Infrastructure
Purpose-built backend. Persistent storage. File processing pipelines. Background jobs. Daily backups. This is production infrastructure.
Async, low-latency
Postgres, 36 tables
14 types, 50+ ext.
Per-artifact queue
Automated
Key encryption
Real-time tokens
All major providers
11 · Chassis & customization
Same data, same flows, twelve radically different aesthetics. Each chassis is a complete visual identity — its own typography, palette, copy, and ambient effects. Switch any time. All chassis are included.
Rainbow LED filament on deep violet-black. A single running spectrum, used with restraint. The future chassis.
Near-black surfaces, teal accent, Outfit + DM Mono. The Nyquest brand — and the chassis you start on.
Indigo and cyan glass. Stars in the background. The default for users who want depth and quiet light.
Warm cream and vermilion. Italic accents. For long-form thinking and slow drafts.
Cobalt with mustard yellow accents. Confident, navigational. For planning and structured work.
Parchment and oxford blue. Serif throughout. For research, citations, and careful argument.
Sage and lavender. Soft, organic, hand-bound feel. For reflection and personal notes.
Green-on-black. Monospace everything. CRT scanlines. For code and command-line minds.
Warm off-white and terracotta. Serif headlines. For writing, editing, and journalistic drafts.
Dark navy and gold with a live ticker. Finnhub-backed market data. For numbers, analysis, and decisions.
Clean white with teal accents. Familiar and crisp. For work that's going in front of clients.
Deep dark with magenta and lime. High-contrast, energetic. For creative work and rapid iteration.
Every chassis renders the same conversations, the same memory, the same artifacts. Switching is purely visual — no state migration, no settings to re-enter.
Each chassis ships its own templates and ambient overlays — quant has the live ticker, matrix has scanlines, apsis has a starfield. Beyond palette, the workspace feels different.
Every chassis is contrast-tuned for readability. Even matrix and studio meet AA on body text. No theme is for show only.
All 12 chassis included on every account. Switch any time from the chassis modal.
12 · BYOK — bring your own keys
BYOK is a first-class feature. Plug in your API keys for any supported provider and your requests go directly to that provider under your billing. No token resale. No middleman markup. No surcharge.
Keys are encrypted the instant you paste them. Per-key nonce stored alongside ciphertext. Decrypted in memory only at dispatch. Never logged, never cached in plaintext, never sent anywhere except the provider you chose.
With BYOK, your request goes directly from Nyquest to the provider's API using your key. You pay the provider's published rate — or whatever volume discount you've negotiated. Nyquest adds zero token markup.
Each provider gets its own adapter handling auth, request shape, and streaming quirks. You can mix BYOK for one provider with hosted billing for others — the dispatcher routes accordingly.
OpenAI (GPT-6 Astra · Astra (batch) · Astra Pro) · Anthropic (Claude Fable 5.1 (batch) · Fable 5.1 · Opus 5) · Google (Gemini 3.8 Flash (batch) · 3.8 Flash · 3.7 Flash) · xAI (Grok 4.6 · 4.5 · Build 0.1) · Any compatible endpoint via custom base URL.
Already have enterprise API agreements with volume pricing? BYOK preserves your negotiated rates. Committed-use discounts, reserved capacity, org-level billing — all stay intact.
Add, rotate, or remove keys any time in Settings → Providers. Each key is scoped to its provider. Mix and match BYOK and hosted billing per provider.
13 · Public API · api.nyquest.ai Live
Same routing, same models, same wallet — accessible programmatically. Issue an API key from your account and integrate Nyquest directly into your apps, agents, or scripts.
POST /v1/chat/completions with streaming SSE. Drop-in
replacement for any OpenAI-compatible client — just point base_url
at https://api.nyquest.ai and pass your nq-v1-... key.
API-key requests skip memory recall and conversation persistence. Each call is independent — no surprising prior-context bleed. Mirrors industry-standard developer-API behavior.
API requests draw from your wallet balance and route through the same
dispatcher tiers as the app. Pin a model with model=... or let the
router choose. BYOK works here too.
Manage keys in Settings → API Keys. Per-key usage and rate-limit tracking. Revoke any time.
14 · Self-hosted · open source · MIT v3.2.8
The compression engine the platform grew from is open source at v3.2.8. Run it on your own infrastructure, behind your own firewall. Prompts never leave your network. Built for privacy-sensitive and air-gapped environments. v3.2 adds a published Docker image — pull from GHCR or build from source.
The public release of the engine Nyquest is built on; the hosted platform has since moved to a later, proprietary build. Six-stage pipeline: normalize, OpenClaw agent mode, cache reorder, regex compression (532 rules across 19 categories with RegexSet prefilter and bounded LRU cache), local LLM semantic stage, auto-scale + forward. Sanitized for public release.
Multi-stage Dockerfile (Rust builder + Debian-slim runtime, non-root user,
tini PID-1) auto-published to ghcr.io/nyquest-ai/nyquest-engine on
every release tag. Or build the single Rust binary from source with the
one-shot installer. Runs on a Raspberry Pi (rules only) or with GPU for the
semantic stage.
MIT licensed. Nyquest-ai/nyquest-rust-fullstack-3.2.0. GitHub Actions CI · 47 / 47 tests passing · Docker auto-publish on tag. Privacy mode by default — no telemetry, no phone-home, prompts never logged.
15 · Browser extension v1.2.0
Chrome extension that intercepts prompts on Claude, ChatGPT, Gemini, and Grok. Applies 281 compression rules locally before send — no proxy, no server, no account required.
Floating overlay on every AI chat showing original tokens, compressed tokens, and savings — updates live as you send messages.
Slider from gentle to aggressive. Test panel previews compression on any text before committing. Tune per workflow.
Popup with session stats, live feed of compressed messages, cumulative savings. See exactly what the extension is doing.
Chrome extension ships 281 rules — a curated subset optimized for browser-side execution. The full engine runs 532 rules.
16 · Comparison
| Product | Where it runs | How you reach it | Best for |
|---|---|---|---|
| Nyquest App | app.nyquest.ai | Sign in to the web app | Day-to-day work, multi-model chat, artifacts, agents |
| Public API | api.nyquest.ai | nq-v1-... bearer token |
Integrating Nyquest into your own apps or agents |
| Self-Hosted Engine | Your machine / VM | Clone on GitHub | Air-gapped or privacy-sensitive deployments |
| Chrome Extension | Your browser | Chrome Web Store | Compressing prompts on existing AI sites you already use |
17 · Roadmap
App · Public API · Self-hosted engine v3.2 · Docker image on GHCR · Chrome extension v1.2.0 · Self-learning tiered routing · Local $0 tier · BYOK · Web grounding · Memory recall · 14 artifact types · Agent mode (beta) · 12 chassis · Audio + image generation · Wallet billing
Encryption-at-rest for messages and memory · Native MCP server interface · T0 self-hosted dispatcher tier (local GPU endpoint) · Outbound webhooks · Batch endpoints
Mobile native apps · Additional provider integrations · Multi-arch Docker images (ARM64) · Expanded agent tool registry
Open the app, grab an API key, clone the engine, or install the extension. They all share the same DNA.