Poco AI / security
Security by design. Privacy you control.
The Poco client runs on your machine: it counts tokens, applies your organization's redaction policy, and installs the editor hooks. The compression itself - and command filtering and document conversion - runs on our server, which is why prompts and commands are transmitted.
Everything Poco sends travels over TLS, authenticated with your account's API key. Nothing is sent anywhere else.
Four things leave your machine, always over an encrypted connection and only ever to our server. What we keep once it arrives is governed by the retention control below.
| What | Why |
|---|---|
| Prompt text | Compressed on the server |
| Commands and their output | Filtered on the server |
| Documents | Converted on the server |
| Session transcript | Powers your dashboard history |
Want secrets stripped before they ever leave? An org admin can switch on client-side secret masking, which redacts known secret patterns from prompts on your machine. It is off by default.
Poco never has to keep your content. One organization setting - Store prompt payloads in Settings - controls it, and your admins decide.
Off: prompts, commands, documents, and transcripts are processed and dropped; only metadata and counts (project name, working directory, model, token totals, active AI tools) reach our database.
On: content is kept for your dashboard history. Prompt text is masked, and everything stored is deleted after 30 days.
The binary ships unsigned today, and the installer clears macOS's quarantine flag so it can run. We would rather you know that than find it yourself: the install script is plain and readable, and the hooks Poco adds to your editor are readable commands, not obfuscated blobs.
Don't want curl | sh? Install the binary alone with POCO_NO_SETUP=1, or authorize non-interactively with POCO_API_KEY instead of the browser. Your key is stored only in ~/.poco/config.toml, readable by you alone.
Both. The Poco AI client on your machine counts tokens, applies your organization's redaction policy, and installs the editor hooks. Compression, command filtering, and document conversion run on Poco's server, which is why prompts and commands are transmitted - always over TLS, authenticated with your account's API key, and sent nowhere else.
A single org-level setting, controlled by your admins, that decides what Poco keeps. Off: prompts, commands, documents, and transcripts are processed and dropped, and only metadata (project name, working directory, model, token totals) reaches the database. On: content is kept for dashboard history, prompt text is masked, and everything stored is deleted after 30 days.
Yes, an org admin can enable client-side secret masking, which redacts known secret patterns from prompts on your machine before they are sent.
Four environment variables, each turning off one feature independently, at any time: - POCO_DISABLE_REMOTE_PIPELINE turns off prompt compression - POCO_DISABLE_REMOTE_FILTER turns off command rewriting and output filtering - POCO_DISABLE_SESSION_CAPTURE turns off session capture - prompt, command, document, and transcript upload - POCO_DISABLE_FOOTPRINT turns off the AI-tool inventory
Security question, or found something we should know about? Contact us - we would rather hear it from you.