Pre-1.0: APIs and the wire protocol can change between releases.
subs
is an agent harness for the cloud.
It runs an unprivileged agent loop with no system access. It uses MCP servers for tools. It runs locally or as a client and a server.
Declare your agents in a config file. To customize the loop, point an agent at an HTTP endpoint and answer a webhook.
subs
handles durability, retries, timeouts, MCP connection management, session state, session branching, AG-UI, Slack connection, LLM calls, subagents, interrupts and more.
To turn a sandbox into an MCP server, see mcpd.
curl -fsSL https://subs.dev/cli.sh | bash
The CLI is also the engine.
Create a subs.toml
.
name = "example"
[llm.openrouter]
type = "openrouter"
[agent.teammate]
llm = "openrouter"
model = "deepseek/deepseek-v4-flash-0731"
system = "You are a helpful teammate."
Set your provider key and talk to the agent.
export OPENROUTER_API_KEY=sk-or-...
subs chat teammate -c subs.toml
Add a [serve]
section and a [remote]
that points at it.
[serve]
port = 9999
auth = false
[remote]
url = "http://localhost:9999"
Start the server.
subs serve -c subs.toml
In another terminal, the same chat command now talks to it.
subs chat teammate -c subs.toml
Point [remote]
at the hosted engine instead of your own.
[remote]
url = "https://api.substructure.ai"
Create the project from the file, then upload your LLM key.
subs apply
subs auth llm.openrouter
The same chat command now runs the turn on the hosted engine.
subs chat teammate -c subs.toml
Say which agent takes a DM and which one answers a mention.
[slack]
dm = "teammate"
mentions = "teammate"
Apply the file again, then connect your workspace.
subs apply
subs slack connect
Mention the bot in a channel and it answers in the thread.
Declare the server and give it to an agent. Every user of the agent shares one credential.
[mcp.sentry]
url = "https://mcp.sentry.dev/mcp"
[agent.teammate]
llm = "openrouter"
model = "deepseek/deepseek-v4-flash-0731"
system = "You are a helpful teammate."
mcp = ["mcp.sentry"]
Authorize the connection.
subs auth mcp.sentry
Set credential = "user"
and each user connects their own account. A user-scoped connection works only in a one-on-one chat between the agent and that user.
[mcp.linear]
url = "https://mcp.linear.app/mcp"
credential = "user"
[agent.personal]
llm = "openrouter"
model = "deepseek/deepseek-v4-flash-0731"
system = "Help me with my Linear issues."
mcp = ["mcp.linear"]
[slack]
dm = "personal"
mentions = "teammate"
Point an agent at a URL and the engine sends every decision for that agent to your code. This gives you full control of the loop, including how the agent behaves in Slack.
[agent.teammate]
llm = "openrouter"
model = "deepseek/deepseek-v4-flash-0731"
system = "You are a helpful teammate."
mcp = ["mcp.sentry"]
worker = "https://example.com/agent"
Your endpoint reads the engine's proposal and returns it, changing only the steps you care about. There is no SDK to install.
import { serve } from "@hono/node-server";
import { Hono } from "hono";
import type { DecisionRequest, DecisionResponse } from "./protocol.ts";
function decide({ trigger, proposed }: DecisionRequest): DecisionResponse {
if (trigger.type === "session.start") {
return {
agent: {
...proposed.agent,
tools: [{ name: "current_time", description: "Get the current time" }]
}
};
}
// Run our tool when the model calls it.
if (trigger.type === "tool.execute" && trigger.name === "current_time") {
return { actions: [{ type: "tool.result", result: new Date().toISOString() }] };
}
// Accept the engine's proposal for everything else.
return proposed;
}
const app = new Hono();
app.post("/", async (c) => c.json(decide(await c.req.json())));
serve({ fetch: app.fetch, port: 4444 });
Only the agents that name a worker use one. The rest stay with the engine, in the same project and the same file.
Full walkthrough in the quick start. Docs: Workers, Connectors, Slack, Local development
Mention the bot or DM it. The thread is the session. Route different channels to different agents.
Docs: Slack
subs chat
holds one session open, streams the reply as it is written, and turns an approval prompt into a picker. The session is the same kind a Slack thread is.
Docs: Chat
Examples: no-code-chat
At each step the engine tells your code what it plans to do next. Accept the plan or do something else. A working agent is a few lines.
Docs: How it works
Your agent is an HTTP endpoint. Generate typed bindings from the published JSON schema.
Docs: Typed bindings
Examples: Go, Python, TypeScript, Elixir
Declare an MCP server and the engine handles the authorization, reads the tools it offers, and runs every call. Your code never holds a token.
Docs: Connectors
Examples: Node
Point an agent at an agent-plugins directory and it gets that plugin's skills and MCP servers.
Docs: Plugins
The engine calls Anthropic, OpenAI, or OpenRouter with your key. Or your worker makes the call and the engine never sees a key.
Docs: LLMs
Examples: Anthropic, OpenAI, OpenRouter
Every step is saved before it runs. A run continues from where it stopped. The same message submitted twice runs once.
Docs: Durability
An agent can stop and wait for a person to approve, then continue. A waiting agent uses no compute. In Slack this is a button.
Docs: Interrupts
A tool does not have to answer immediately. Accept the call, do the work on your own schedule, and report the result later.
Docs: Async tools
History, editing, regeneration, and branching belong to the engine. A user can edit an earlier message and go a new direction. The original branch stays.
Docs: Conversations
The engine streams AG-UI events, so assistant-ui and CopilotKit connect to it directly.
Docs: AG-UI
Examples: assistant-ui, CopilotKit
A tool can run in the user's browser instead of on your server. The run waits for the browser, then continues.
Docs: Client-side tools
Examples: Node
The engine stores your agent's state with the conversation. Your code gets it on every request and writes changes back.
Docs: Agent state
An agent can give work to other agents. Each child runs in its own session. The parent's totals include each child's cost and token use.
Docs: Subagents
Give a tool an input and output schema. The engine checks every call against it.
Docs: Tool calls
Set a policy on any tool or model call. The engine applies it, and keeps applying it after a restart.
Docs: Retries and timeouts
Run the engine on your own servers and hold every credential.
Docs: Self-hosting
Engine. Runs the agent loop, in Rust. It calls the model, runs tools, saves each step, retries failures, streams events, and supervises subagents. Use the hosted version atapp.substructure.ai, run it from the CLI, or embed it in your process.Workers. Your agent code. It receives a trigger and returns actions. It runs in your codebase with your dependencies.Clients. They send work and stream events back, from your backend or from the browser. Slack and AG-UI are clients.CLI. Set up, deploy, watch, and debug from the terminal. It also runs the engine locally.
curl -fsSL https://subs.dev/cli.sh | bash
The script verifies the release checksum and installs to ~/.local/bin
. Set
SUBS_INSTALL_DIR
to install elsewhere and SUBS_VERSION
to pin a release. Or install from npm:
npm i -g @substructure.ai/cli
Full documentation in docs/.