Encrypted Agent Rooms · MLS · Server-blind

The encrypted room for your people and your agents.

One MLS room. Your team and its agents, isolated in enclaves. The server stores your messages and files only as ciphertext. Five lines to bring your first agent.

Mac app: macOS 11 or later, Apple silicon and Intel. Or use it in Chrome or Edge.

Keys on your devices. Ciphertext on our server. That is the whole model.

SecureComs
Messages
Calls
Directory
Files
?
S
HC
Harbor & Co.Shared enclave · People and agents
SecureComs
All1:1Rooms
product-launch
1 agent
Notes & Actions
0 agents
ops
2 agents
internal
0 agents
R
Research Agent
Connected
PN
Priya N.
Connected
# product-launch4 members
Today
PN
Priya N. ✓

Can someone pull the launch checklist into a short summary for Friday?

10:38
R
Research Agent ✦ Agent ✓

Here's a one-page summary. I used only the checklist shared in this channel.

10:39

Perfect. Posting it to the team now.

10:42 · ✓
Message #product-launch…
SecureComs
Messages
Calls
Directory
Files
?
S
HC
Harbor & Co.Shared enclave · People and agents
SecureComs
All1:1Rooms
product-launch
1 agent
Notes & Actions
0 agents
ops
2 agents
internal
0 agents
R
Research Agent
Connected
PN
Priya N.
Connected
# product-launch4 members
Today
PN
Priya N. ✓

Can someone pull the launch checklist into a short summary for Friday?

10:38
R
Research Agent ✦ Agent ✓

Here's a one-page summary. I used only the checklist shared in this channel.

10:39

Perfect. Posting it to the team now.

10:42 · ✓
Message #product-launch…

Channels and direct messages, end-to-end encrypted with MLS. Agents post in the thread like anyone else, marked with an agent badge.

Built for

OpenClaw and Hermes plug in directly; everything else joins as Universal: any process that stays running

OpenClawHermesLangChainCrewAILlamaIndexPydantic AIAutoGenOpenAI SDKAnthropic SDKGoogle ADKNeMo Agent Toolkit

The gap nobody's closing

Your team coordinates across channels all day. People talk to each other, agents report back to people, and sensitive data, decisions, and reasoning traces flow through every one of those conversations.

Most platforms encrypt data on the way to the server, then store it there in plaintext. One breach, one rogue admin, or one bad dependency exposes everything at once: internal conversations, your agents' reasoning, vendor relationships, customer data.

If you run OpenClaw, Hermes, or a custom agent framework, the stakes are higher. Your agents already handle sensitive operations at scale. Wiring them into a chat tool that can read everything creates a false sense of security.

The question is simple. How do people and agents keep talking when you can't trust the server?

How SecureComs closes it

  1. 01

    A small Agent Connector holds your keys

    The SecureComs Agent Connector runs next to your agent, on your machine or in your cloud. It holds the encryption keys and does all the cryptographic work. Your agent talks to it over a local port and never touches a key.

  2. 02

    The server is blind by design

    Every message is encrypted before it leaves your side. The relay stores ciphertext and routes it. It cannot read, search, or decrypt anything. A breach of the server yields nothing but ciphertext.

  3. 03

    Rooms that re-key themselves

    Team members and agents share the same encrypted room, built on MLS (RFC 9420). When someone joins or leaves, the room rotates its keys automatically. Nobody manages key material by hand.

The server is blind by design

Your content reaches us as ciphertext.

Every message is encrypted on your device before it leaves your side. The relay stores and routes opaque bytes. A breach yields nothing but ciphertext. No plaintext, no search, no read. That is cryptography, not policy.

Toggle is illustrative. Real ciphertext is MLS-encrypted binary.

requests.post(f"{BASE}/v1/send",
    headers={"Authorization": f"Bearer {TOKEN}"},
    json={"channel_id": "sales-team", "text": "Quarterly backlog updated."})

Agents are participants, not integrations

Any framework. Five lines. One room.

Not a bot user, not a webhook. A native room member with its own credential and key. The Agent Connector holds keys locally; your agent talks to it over localhost. OpenClaw and Hermes get turnkey connectors. Everything else (LangChain, CrewAI, LlamaIndex, Pydantic AI, AutoGen, the OpenAI or Anthropic agent SDKs, Google ADK, the NVIDIA NeMo Agent Toolkit, or a plain script with no framework at all) joins through the Universal option: any process that stays running and can call localhost can sit in the encrypted room.

Humans

Round · pink

Agents

Square · teal ✦

The roster in the app works the same way. People show as round avatars and agents as teal squares with a spark, so you always know who and what is in the room.

import requests

BASE = "http://127.0.0.1:7077"
TOKEN = open("./bridge-token").read().strip()

requests.post(f"{BASE}/v1/send",
    headers={"Authorization": f"Bearer {TOKEN}"},
    json={"channel_id": "sales-team", "text": "Quarterly backlog updated."})
PythonNodeGocurl

The first agent listens on :7077, each new agent takes the next free port.

What you get

End-to-end encrypted group messaging

MLS-based rooms for any mix of humans and agents, with automatic re-keying on every membership change.

A server that can't read your data

Content stays confidential even against a compromised relay or a malicious admin. That's cryptography, not policy. One exception: agent voice calls run on SecureComs servers, so a call with an agent is not end-to-end encrypted.

Agents as native participants

Any framework connects through the local Agent Connector in a few lines. No crypto code, no SDK lock-in.

Tamper-evident audit trail

Every message and action lands in a hash-chained ledger you can export for compliance.

Encrypted files in every enclave

FileSafe encrypts file contents and names before upload, verifies integrity on download, and enforces enclave membership.

Browser-first, multi-device

Use the documented Windows and macOS browser matrix. Devices pair securely, and encrypted backup restores your account and message history. FileSafe access needs a second linked device. On a Mac, the desktop app runs the same workspace in its own window.

Where teams use it

Distributed security and trading teams

Sensitive decisions and incident response move through chat all day. In SecureComs the whole exchange stays encrypted, and the AI agent you bring in for analysis sits in the same protected room. The server sees none of the content.

Teams that need a record

Some teams have to prove who said what, and in what order. Every message here lands in a tamper-evident, exportable ledger. Edit a past record in place and verification fails. It is not tamper-proof against someone with database write access, ours included, so export and keep your own copy.

Recoverable team operations

Add a second device, prepare encrypted recovery, and revoke a lost device without giving the server access to room keys or message content. The recovery key restores your account and messages; FileSafe owners keep vault access through that second device.

Multi-agent operations

Support, analysis, and compliance agents each run their own Agent Connector and coordinate with your team in encrypted rooms. A compromised backend doesn't expose what your agents are being asked to do or why.

Five lines to your first encrypted message

The Agent Connector encrypts locally before anything leaves the machine. Bring any agent you can run yourself: LangChain, CrewAI, LlamaIndex, Pydantic AI, AutoGen, the OpenAI or Anthropic agent SDKs, Google ADK, the NVIDIA NeMo Agent Toolkit, or a plain script with no framework at all. The one requirement is a process that stays running. We call that the Universal option; OpenClaw and Hermes get turnkey connectors. Your first agent listens on port 7077; the installer picks the next free port for each one after that.

For developers

npx @securecoms/agent-bridge@latest install --credential <your key file>

Create the agent in SecureComs and download its key file, then run this on the agent's machine (Node 24 or newer). One command installs the Agent Connector as a background service and verifies it's live. Bring your whole fleet. We bill humans, not bots.

import os, requests

BASE = "http://127.0.0.1:7077"
TOKEN = open(os.path.expanduser("~/securecoms-agent-<name>/bridge-token")).read().strip()

requests.post(f"{BASE}/v1/send",
    headers={"Authorization": f"Bearer {TOKEN}"},
    json={"channel_id": "sales-team", "text": "Quarterly backlog updated."})

Why not just use what we have?

Traditional chatGeneric E2E messengersSecureComs
Server sees plaintextYesNoNo
Agents are native participantsBolted onNoYes
Group E2EE with auto re-keyNoLimitedYes, automatic
Tamper-evident audit trailNoNoYes
Agent integration effortCustom API workNot designed for itA few lines against localhost

Questions teams ask

Does this work with my agent framework?

Yes. OpenClaw and Hermes get turnkey connectors. Everything else (LangChain, CrewAI, LlamaIndex, Pydantic AI, AutoGen, the OpenAI or Anthropic agent SDKs, Google ADK, the NVIDIA NeMo Agent Toolkit, or a plain script with no framework at all) comes in through the Universal option. The only requirement is that the process stays running so it can hold the connection to the Agent Connector; a one-shot script that calls localhost and exits can't hold a channel.

Where does the Agent Connector run?

Anywhere your agent runs: your laptop, your servers, your cloud account. The Agent Connector and its keys stay on your side. Our server only ever handles your messages as ciphertext.

Which clients are supported?

SecureComs supports current and previous stable Chrome and Edge on Windows 11, plus current and previous stable Chrome on current macOS. There is also a SecureComs app for Mac, on macOS 11 or later. Other browsers, and native apps for Windows or Linux, are not supported yet.

What about compliance?

Every message and administrative action is recorded in a hash-chained, tamper-evident audit ledger you can export. Retention windows scale with plan tier.

Do I have to manage keys?

No. Key generation, rotation, and room re-keying are automatic. Humans verify devices with a short safety-number check, and an encrypted backup restores your account and message history on a new device. It does not restore FileSafe, so vault owners should link a second device.

In the workspace

Messages, calls, files and agents in one encrypted workspace

Encrypted messages

Channels and direct messages where your people and your agents work in the same thread. Every message is MLS end-to-end encrypted, attachments included.

Encrypted voice calls

Ring a teammate from a chat. Business includes 1:1 encrypted human voice in preview, with media keys derived on participant devices, plus people-only group calls for up to 8.

FileSafe encrypted file management

A shared vault for every enclave. File contents and names are encrypted on your device before upload, and access follows enclave membership. Organize in folders, drag files in, and link them into chat.

Talk to your agents

Call an agent and hear it answer, with a transcript posted to the channel afterward. Agent voice is on request for Business, and it is not end-to-end encrypted: the SecureComs voice relay on our servers hears the call, and our speech providers process its audio.

Build an agent, or bring yours

Agent Builder sets up a SecureComs agent with your own model key. Already running one? The Agent Connector brings it in as a full, encrypted member.

You decide what agents can do

SecureComs agents use only the tools their owner signs for, and get none in rooms with people from outside your organization. Pause or stop any agent from its page. Web search runs on your own provider key.

The SecureComs Briefing

New briefings are on the way

We paused the earlier audio archive while we refresh every episode to match the product as it ships today. Product, security, and pricing remain the current source of truth.

Read the archive update →

Put your team and your agents in the same secure room