You know who else thinks context window size is important? Claude does.
No more context-window limits. No RAG. No lossy retrieval guessing. Awarity reads every token you throw at it, matches GPT-5.4 on the benchmarks — then runs the whole pipeline offline on open models and the hardware you already own. No API key. No cloud. Nothing phoned home.
Awarity now runs end-to-end on open AI models on your own computer. Install the app and it reads, maps, and answers across your entire document set — without ever touching the cloud. No API key. No uploads. No per-query fees. The most private way to put AI on the documents you can't send anywhere.
Every document and every query stays local — by default, not as an enterprise add-on. Awarity has no server to send your data to.
Works the moment you install it, on free open models. Add an OpenAI, Anthropic, or Gemini key only if you specifically want a cloud model.
Runs with no internet connection at all. Built for legal, healthcare, finance, and government data that can never leave the building.
Native LLMs like Claude or ChatGPT cap out at 500K–1M tokens. Drop in a large dataset and you're already over the limit — the model starts hallucinating or refusing. Awarity has tested beyond 400 million tokens.
Retrieval-Augmented Generation picks what to retrieve — and guesses wrong. Embeddings compress meaning, vector search misses edges, and the answer you get is only as good as what was fetched. Awarity reads everything, every time.
Most AI tools require uploading documents to a third-party cloud. Awarity runs on-prem or fully offline. Your contracts, financials, and patient data never leave your environment.
Drop in any documents — PDFs, Word files, spreadsheets, CSVs. Awarity chunks and indexes them into a local catalog. No cloud upload required.
ECW sends every chunk through a fast model — running locally on your Mac, or in the cloud — simultaneously. Each call is small, under the context limit, so no document is truncated. Notes are collected from all chunks.
The notes — not the raw documents — are synthesized by your chosen model, local or cloud. The infer context stays small regardless of catalog size — which is why ECW runs free on your own machine, or 68–92% cheaper in the cloud.
You know who else thinks context window size is important? Claude does.
Download Awarity for Mac and start querying your documents in minutes. Ingest files, build catalogs, run queries — no command line required. Free, self-contained, and runs entirely offline on your machine.
The Awarity CLI drops into any existing workflow. Run awarity ask, awarity extract, or awarity for-each inside scripts, CI/CD jobs, or scheduled tasks. If you have a pipeline, Awarity plugs in.
Deploy Awarity as an Azure Function, AWS Lambda, or Docker container. First-class TypeScript and Node.js support. Call document reasoning from any application or service.
An early unsigned build is available for Windows x64 and ARM64. Windows will show a SmartScreen warning — click "More info" then "Run anyway" to install.
Awarity runs entirely on your machine. Bring your own API key, ingest your documents, and start getting answers — no SaaS subscription, no data upload, no vendor lock-in.