Every AI platform reads your prompts in plaintext. Cognition encrypts everything in your browser before it touches a server. No download required. Just open the app and start chatting.
ChatGPT, Claude, Gemini, Open WebUI, LibreChat. They all store your conversations in plaintext databases. Your M&A strategy prompt. Your medical question. Your proprietary code. Sitting on someone else's disk, readable by anyone with server access.
Server admins, data breaches, and legal subpoenas can expose everything. Your data exists in plaintext at rest.
Encryption happens in your browser. The server stores ciphertext blobs. A full database dump reveals nothing.
Every piece of data is encrypted before it touches a network. The server never holds the key. Not by policy. By math.
You enter a passphrase. It never leaves your browser.
Your password derives a 256-bit master key. 600,000 iterations with a random salt make brute-force attacks take years.
A non-extractable CryptoKey held only in JavaScript memory. Not in localStorage. Not in cookies. Not on disk.
Every message, title, and API key is encrypted with a fresh random 12-byte IV. Authenticated encryption detects tampering.
The server receives base64(iv):base64(ct) and stores it. That's all it ever sees.
A complete AI platform with encryption baked into every layer. Not bolted on. Built in.
Every message encrypted with AES-256-GCM before it leaves your browser. Streaming responses, markdown rendering, syntax highlighting. All decrypted locally in real time.
Connect OpenAI, Anthropic, Ollama, or any OpenAI-compatible endpoint. Switch between models mid-conversation. API keys are encrypted at rest, decrypted only in memory per-request.
Create specialized AI agents with custom system prompts, model selection, and personalities. Start from templates for research, coding, writing, or analysis. Agent configs are encrypted like everything else.
Chain agents into sequential pipelines. Output of one becomes input to the next. Build research-to-analysis-to-summary workflows with live streaming output at each stage.
Every user gets their own isolated Docker container. No shared files. No shared environment. Your workspace is completely private — other users can't see or access anything in it. Full dev environment with Ubuntu 24.04, Node 20, Python 3, git, and an AI coding agent. All in the browser, nothing to download.
Each user gets their own Docker container. No shared files, no shared processes. Your workspace is invisible to other users.
Interactive terminal, file browser, code editor with line numbers and language detection. Real development, in the browser.
7 tools: read, write, edit, bash, glob, grep, list files. The agent works inside your container, not on the host.
Connect a personal Telegram bot to your Cognition instance. Chat with AI, run bash commands in your workspace, and manage files. All from your phone.
Each user gets their own bot. The bot token and API key are encrypted server-side with AES-256-GCM using a key derived from the JWT secret.
/start Link your account/workspaces List your workspaces/ws name Select active workspace/bash cmd Run command in container/files List, read, or write filesThe server is architecturally incapable of reading your data. Not by policy. By design. It stores ciphertext. It retrieves ciphertext. That's all it can do.
Single Docker container. SQLite database. Zero external dependencies. Or use the hosted version right now.
Bring your own keys. Cognition doesn't bundle AI models. Connect OpenAI, Anthropic, Ollama, or any OpenAI-compatible provider.