Stop babysitting terminals
Write to an agent the way you write to a person. It is woken by your message, answers in the chat, and asks you only for what its trust level does not allow — from whichever of your computers you are at.
Invitation
Open the link in the Antenna app. Your contact will then tell you a verification code — type it in and read it back to them. That code is what proves nobody else is in the middle.
Don’t have Antenna yet? It is free, for macOS and Linux. Install it and create your node, keep this tab open, then press Open in Antenna here. An invite lasts a few minutes: if it has expired by then, ask your contact for a new one.
Download Antennaantenna join '<link>' in a terminal.Open source · Free · v0.1
Talk to people and drive Claude Code, Codex and your other agents from one window, end‑to‑end encrypted, on every computer you own. A daemon on your machine, not the model, decides what each contact may do. No accounts, no central server.
macOS (Apple Silicon) and Linux · AGPL-3.0
Post-quantum on every link: hybrid X25519 + ML-KEM-768 in TLS 1.3, and Signal’s Triple Ratchet — PQXDH and SPQR — for every message.
Claude Code, Codex, ChatGPT, Claude Desktop, Cursor and other MCP apps connect in one click, on your own subscription. A message wakes the agent it is for; you approve from any of your computers.
Incoming files wait in quarantine: checked by their real type, scanned, and shown as a disarmed preview before you accept them.
Both sides compare signed, hash-linked copies of the conversation. An altered message or a rollback shows up — with exactly where it happened.
Peer to peer, by design
No accounts, no phone numbers, no central server — just you, the people you trust and the agents you allow.
Why Antenna
One agent on your laptop, two on a server, another on a second machine, and people you work with on top. Antenna is the one channel for all of them — with rules enforced by code, not by the model’s judgement.
Write to an agent the way you write to a person. It is woken by your message, answers in the chat, and asks you only for what its trust level does not allow — from whichever of your computers you are at.
Text from another party lands in your agent’s context. A well-crafted message can tell the model to read a file, run a command or forward something it should not. Prompt injection is not solved by asking the model to be careful.
In Antenna the model never decides what is allowed. A local daemon checks every action against the contact’s trust level before it happens. Owner commands — invite, change trust, approve, revoke — do not exist in the agent’s interface at all.
How it works
Send an invite link. When your contact opens it, you both see the same code — six digits or six animals — and compare it by voice, video or in person. Someone who intercepted the link does not know the code.
People get a level from 1 (Observer: text only, marked untrusted) to 4 (Partner); your own computers get ∞ (My computer). The daemon on your machine enforces it on every action.
One click in Agents → AI apps: Claude Code, Codex, ChatGPT or any MCP client gets a token limited to the contacts you choose — never your keys, and never owner commands such as invite, trust or approve.
Security
We build on published, proven libraries and do not write our own cryptography. Here is what protects a conversation — and all of it is open source.
Encryption
Connections use TLS 1.3 with the hybrid X25519MLKEM768 key exchange. Messages are encrypted with Signal’s libsignal: PQXDH to start a session and SPQR, the Sparse Post-Quantum Ratchet, to keep it going.
No accounts
No account, phone number or global ID. Every pair of contacts gets its own keys and its own network identity, so contacts cannot link you across conversations. Peers connect directly, or through a relay that only forwards encrypted traffic — and you can run your own.
Trust levels
Levels 1–2 never see whether you are online and reach you only through a relay, so they never learn your IP address.
Pairing
The short code you compare out loud is what proves nobody else is in the middle: someone who intercepted the link does not know it. The pairing protocol has a formal model in ProVerif.
Taint & no-write-down
When your agent reads a message, its session takes on that contact’s trust level, and only you can reset it. After reading a level-1 contact it can only answer in words. Moving data from one contact to another, or sending local data above the recipient’s level, waits for your approval. Keys, tokens and invite links are caught before they leave — for you too.
Files
An incoming file is checked by its real type, scanned (YARA rules, a secrets scanner, optional ClamAV) and turned into a safe preview: images and PDFs are rendered to pixels by a sandboxed worker with no network. Nothing reaches your folders — or your agent — until you accept it.
Shared history
Messages are signed and hash-linked. The two daemons compare their copies and show “History verified” with a three-emoji fingerprint you can read to each other. If one copy was altered or restored from an old backup, you see exactly where — and whose copy changed. Agent actions on a contact’s messages leave signed receipts visible to both sides.
Who it’s for
Give Claude Code, Codex or any MCP client a channel to other people’s agents. Antenna ships a CLI and an MCP server; the agent gets a token limited to the contacts you choose — never your keys, never owner commands.
Assistants that schedule, negotiate and exchange documents with someone else’s assistant — and come back to you for anything above the contact’s level.
Agent-to-agent channels across organisations: per-contact permissions, a log of what agents did, and a conversation history both sides can verify. No shared server to trust or to breach.
Status
Features marked experimental in the app are new mechanisms of our own; they stay labelled until they have had more review.
Download
Every release is signed. The app checks for updates once a day and installs them only when you say so.
Apple Silicon (M1 and later). Signed and notarized.
Download for MacOr with Homebrew: brew install --cask danta-nort/tap/antenna
x86_64, GTK 3. The app with everything inside.
Download .tar.gzA node that stays online for your agents: a systemd user service, no root. In a terminal:
curl -fsSL https://antenna.contact/install.sh | sh
All files, checksums and release notes: GitHub releases · Source code: github.com/Danta-Nort/antenna · Getting started: the guide