Sivra vs Sencha

Answers you can stand behind. Sivra is a verified answer engine. Ask a question and Sivra investigates it across sources, tests every claim against the evidence it fetched, and delivers one clear answer you can trace. Anything Sivra can't trace to a source doesn't make it in. THE ANSWER Every inquiry ends in a single, direct answer with a stated confidence level — and three lenses beneath it: - Evidence — the claims that support the answer, each linked to its source - Caution — what could change the answer, and what to watch for - Action — what to do next, ordered by effort CHOOSE YOUR DEPTH - Glance — one pass, about two minutes - Survey — two passes, deeper evidence - Expedition — three passes, exhaustive YOUR CONSTELLATION Everything Sivra has verified for you, connected. Each completed inquiry adds findings to your Constellation. Browse it as a living map, or ask questions across everything you've already verified. SHOW THE WORK - Every finding lists its sources; tap through and read them yourself - Findings carry evidence, relevance, and confidence scores — the weighting formula is printed in the app - A full written report accompanies every inquiry HONEST BY DESIGN Sivra's answers are AI-generated and can be wrong. The app says so, every claim is traceable, and nothing is presented with more confidence than the evidence supports. Credits are one-time purchases — no subscription. A Glance costs one credit; deeper inquiries cost more.

A native LLM client for on-device inference, LLM APIs, and self-hosted servers, built around a minimal, responsive interface. Download a supported model and chat offline without an API key or account. Or connect OpenRouter, direct providers, and compatible endpoints using your own credentials. On-Device Models • Download models from the built-in catalog, including Gemma 4, Qwen 3.5, Bonsai, and LFM 2.5 • Choose model sizes and quantization options to suit your device • Configure context window, reply length, and image detail where supported • Use streaming, thinking traces, image attachments, and web tools with compatible models • Reduce reprocessing of earlier messages with on-disk prompt caching Model capabilities and performance depend on the selected model and available device memory. Connections and Models • Connect OpenRouter, OpenCode, and direct providers • Add OpenAI- or Anthropic-compatible endpoints, including self-hosted runtimes such as Ollama and LM Studio • Use Chat Completions, Responses API, or Messages API • Choose an on-device or connected model per chat • Browse model catalogs and inspect context size, output limits, pricing, and capabilities where available • Configure reasoning effort, prompt caching, routing, and model tools where supported Web Search and Fetch • Use the included free web search via Markdown.new • Or configure Brave Search, Tavily, Exa, Serper, SerpApi, Parallel, or Keenable • Choose search-depth presets for Exa and Tavily • Fetch pages on device or through Markdown.new or Firecrawl • Configure fetch providers and fallbacks independently Files and Output • Attach photos, documents, and PDFs • Send PDFs natively, extract embedded text, run on-device OCR, or render pages as images • Read responses with formatted Markdown, code, mathematical formulas, and tables • Copy generated tables as a table, Markdown, or a complete image Voice Input • Use Apple Speech for on-device dictation • Download local transcription models • Connect API-based transcription providers The app is free, with no ads or app subscription. On-device models require no provider account or API key. Connected services are subject to their own pricing, limits, and data policies.