v0.1 self-hostable Apache-2.0 core

The SSH of the
agent world.

agent-exec gives an AI agent a self-describing, ACL-controlled entry point into a machine. Give it a URL and API key. It reads/SKILL.md, checks/api/acl, and executes allowed commands through/api/exec.

Developer preview boundary: not a sandbox, not SSH-compatible, and not an SSH replacement. Fresh installs only allowaexec --version. Use localhost, VPN, firewall, or TLS-terminated trusted networks.
agent handoff

Install, start, share. Then paste.

aexecis the official command.aeis the short alias for daily use.

bash
# 1. Install
$ npm install -g @to-agent/agent-exec

# 2. Set up local config and API key
$ aexec setup

# 3. Start serving
$ aexec start

# 4. Generate a prompt for an AI agent
$ aexec share

# Optional: expose installed AI tools as plugins
$ aexec starterkit
$ aexec restart
AI install prompt
Install agent-exec on this machine.

Run:
1. Check that Node.js and npm are available.
2. Install globally:
   npm install -g @to-agent/agent-exec
3. Run:
   aexec setup
4. Start the server:
   aexec start
5. Run:
   aexec share
6. Show me the generated share prompt.

Do not edit project files unless needed.
Do not expose agent-exec to the public internet.
Do not use --public unless I explicitly ask for network access.
Do not add broad ACL rules such as allow "*".
Fresh installs should only allow:
  aexec --version

If any command fails, stop and show me the error plus the next recommended command.
aexec share
You have access to a machine through agent-exec.

URL: http://<agent-exec-host>:3333
API_KEY: <api-key>

Start here:
http://<agent-exec-host>:3333/SKILL.md

A machine that explains itself to agents.

agent-exec does not require a special SDK or model-specific integration. The machine publishes a small HTTP entry point and the agent follows the documents.

01

Read /SKILL.md

The public entry point tells the agent how to start.

02

Inspect /api/acl

The agent checks what commands are allowed before executing.

03

Discover /api/plugins

Optional plugin documentation is loaded only when the agent needs it.

04

POST /api/exec

The server executes only what the ACL permits.

Agent receives URL + API key GET /SKILL.md GET /api/acl GET /api/plugins POST /api/exec allowed operation runs on the machine

Extend with plugins and skills.

Plugins add tool-specific documentation and optional command behavior. Skills keep detailed usage out of the initial prompt and let agents load detail only when needed.

plugin commands
$ aexec plugin list
$ aexec plugin create --name=mytool --command=mytool
$ aexec plugin doctor

argv, not shell strings.

/api/execaccepts JSON body arguments only. GET requests and query-string commands never execute.

JSON body only

Commands are sent as{"args":["command","arg"]}.?cmd=and?args=are not execution inputs.

No shell interpretation

agent-exec executes argv. Shell operators such as&&,;, pipes, redirects, and subshell syntax are not interpreted by agent-exec itself.

Deny before allow

ACL matching usesargs.join(' '). Plain strings are exact matches; use explicit glob or regex rules for broader matching. A rule likecmd *allows any arguments tocmd. Deny rules win before allow rules.

Trusted plugins are host code

Trusted plugins should be reviewed like code running as the agent-exec OS user. Do not install unreviewed trusted plugins.

The agent discovers. The server decides.

agent-exec is default-deny. Fresh installs only allowaexec --version. Use ACLs, least-privileged OS users, and network controls. It is SSH-like access for AI agents, not SSH-compatible and not an SSH replacement.

Do not expose plain HTTP agent-exec to the public internet. Use localhost, VPN, firewall, TLS termination, or another trusted network boundary. Treat the API key as machine execution capability and rotate it after canary tests.

Any HTTP-capable agent can start here.

If your agent can make HTTP requests, it can start with agent-exec.