Agent Farmbeta Join early access

District X of XEight things

Safe and yours alone

Guards stop what an agent should not do, and nothing about your work comes to us.

A quiet home office: a desk, a chair and a lamp by the wall

Your work stays on your machine. The free version never contacts us; a paid licence checks its key once a day, and that is the whole message. Your engines talk to their own providers, and anything else Agent Farm reaches is a service you switch on. On the machine, guards stop an agent before a command runs, not after: one for the shell, one for disk searches, one for permissions, one for keys and one for the browser.

17 Local

0 bytes

of your work to us. Ever.

  • Free: nothing to us at all. No account with us, no request to a server of ours. It runs inside VS Code and reads each CLI's own files on disk.
  • A paid licence: one check, once a day. The whole message is beside this. If it cannot reach us, it keeps working for 30 days.
  • No telemetry, no analytics. We don't know which features you use, how often, or on what.
  • Secrets stay in the OS keychain. An account is a config folder, not a copied credential.
  • Live hooks listen on 127.0.0.1 only. The phone page is yours to switch on, on your own network.

The licence check, wholepaid licence · once a day

→ { "key": "AF-7Q2K-…-M4XD", "device": "a91f…e07b", "version": "3.931.0-beta" }
← { "valid": true, "until": "2026-11-12" }

Never in it: your code · prompts and answers · transcripts · file, folder and project names · account names · costs and tokens · which features you use, or how often.

Your engines talk to their own providers, as they always do. Anything else Agent Farm reaches is a service you switch on yourself: a voice for the briefing, a media model in Studio, Jev for Gatekeeper, Telegram.

Built like infrastructure.

Every number stated on this page comes from a real screen of the app or from its source. The moving parts are demos, with demo data.

35,600+tests behind 1,053 releasesTechnical DNA · CHANGELOG.md
0runtime dependencies, 0 telemetrypackage.json · README
⑂ 92legs in one real relay chainConsole · session strip
5engines, each measured against a real binaryEngines page
40%the context line where a leg hands overcontextHandoverPct
602commands and 243 settings, in one extensionpackage.json
X·1

On your machine

It runs inside VS Code and your work stays on your disk. The live hooks listen on 127.0.0.1 only.

The machine, drawn

What it solves

Whatever watches your agents sees all of your work: the code, the prompts, the answers and what they cost. None of that has to leave your machine for the watching to work.

How it works · pick a step

The hooks go into Claude Code's settings.json beside your own entries. The first write keeps an .agentfarm-bak backup, and Remove Live Hooks takes out only Agent Farm's entries.

Settings · 3
SettingDefaultWhat it does
agentFarm.liveMonitoronRuns the live event listener.
agentFarm.livePort8377The listener's port on 127.0.0.1. Installed hooks follow a change without a reload.
agentFarm.planUsageRefreshMinutes5 minHow often an idle farm reads your plan's usage. 0 = only when you ask.
X·1Inside VS Code1 / 5
X·2

No telemetry

No analytics, no usage statistics: we don't know which features you use, how often or on what. Free never contacts us; a paid licence only checks its key.

The licence check, whole

What it solves

Most tools count how they are used and send the count home. You are left to trust what is in it.

How it works · pick a step

Export Traces (OpenTelemetry JSON) writes your sessions to a file on your disk. Where that file goes is your call; Agent Farm sends it nowhere.

Settings · 4
SettingDefaultWhat it does
agentFarm.digestTtsModelemptyThe fal.ai voice model the briefing is read with.
agentFarm.embeddingsProvideroffSemantic search through gemini or openai, Ollama included.
agentFarm.notifyWebhookUrlemptyA webhook to forward notifications to.
agentFarm.kapici.dispatchoffAsks Gatekeeper which agent takes a request. Each use of Gatekeeper has its own switch, and all start off.
X·2Free1 / 5
X·3

ShellGuard

Before a shell command runs, the shapes that garble or hide it are refused: non-ASCII, backticks, long heredocs, long quoted text. The agent is told the safe way: write the text to a file.

What it solves

Agents write long shell commands. Some arrive garbled, a character re-encoded on the way, and some run more than they show, a second command inside a backtick. Neither is visible until it has run.

How it works · pick a step

The backtick rule applies where the shell is bash: Claude Code, Git Bash. Codex's shell on Windows is PowerShell, where a backtick is the escape character, so there it is not refused.

X·3Before it runs1 / 4
X·4

BridgeGuard

An agent that goes searching the disk for a session by its id is stopped and sent to the bridge, which reads it properly.

Session 7c41e2a0, picked up by its id

What it solves

An agent asked about an old session goes looking for it on disk: a recursive search through every CLI's folders for its id. It burns context and quota, and those folders and their formats change with each CLI release.

How it works · pick a step

Each stop is logged and leaves a mark on that session's Console card.

X·4The hunt1 / 5
X·5

Permissions as shown

The permission a card shows is the one in force; if a policy forbids it, the session is refused, never quietly downgraded. A lint finds blanket allows and dangerous patterns.

What it solves

When a card says one permission and the process runs under another, a session you set to bypass can sit for an hour on a question nobody sees, and one you thought would ask goes ahead.

How it works · pick a step

An agent can answer a session's question over the bridge, but it can never grant a tool permission. That stays your call, in the panel.

Settings · 2
SettingDefaultWhat it does
agentFarm.permissionLintonAudits the permission rules in each agent's .claude/settings(.local).json; findings go to Insights.
agentFarm.launchDefaults{}The model, effort and permission mode every interactive session carries. An empty field adds no flag.
X·5One label1 / 5
X·6

Keys kept out

Route keys are scrubbed from whatever a run prints, and Gatekeeper's log keeps only a hash and a length of what it read.

The vault, in Any brain

What it solves

A key handed to a run ends up in what the run prints: a request line, an error, a config dump. Archived, that output is your key in plain text in a file.

How it works · pick a step

A secret can be marked farm only: Agent Farm still uses it, but no agent's task receives it. The Gatekeeper key starts that way. And a key found in plain text in a config file is reported, so you can move it to the vault.

Settings · 1
SettingDefaultWhat it does
agentFarm.mediaAuthSecretFAL_KEYThe name of the secret that holds the media key. The setting holds the key's name, not the key.
X·6The keychain1 / 5
X·7

Browser on a leash

A browser step opens only the sites on its allow list, or fails without running, and asks you before each run unless you chose otherwise.

What it solves

An agent with a browser can follow a link anywhere. A step that runs at night has nobody watching where it goes.

How it works · pick a step

The agent's prompt carries hard rules as well: open no link off the list, never make up a sign-in, and report NO BROWSER MCP when there is no browser. A login wall on a recipe step is reported as LOGIN NEEDED, never typed into.

Settings · 2
SettingDefaultWhat it does
agentFarm.browserAllowHosts[]Hosts every browser step may open, beside the step's own list.
agentFarm.browserApprovalaskask: approve each run, with the URL and objective shown. auto: no question.
X·7The step1 / 5
X·8

Superpowers

Engineering disciplines on disk, such as tests first and systematic debugging, with quality gates.

What it solves

An agent left to itself patches the symptom and says it is done. Loading a whole engineering method into every session to stop that costs tokens on every turn, even when the work is a lint sweep.

How it works · pick a step

Agent default is not off: it hands the choice back to the agent's own setting, which is what every task written before the switch existed still says.

Settings · 2
SettingDefaultWhat it does
agentFarm.superpowersPathemptyThe disciplines' folder. Empty: _SKILLS/superpowers beside your agent folders.
agentFarm.superpowersDefaultsdeveloper: onOn or off per agent, by exact name. An agent not named starts without it.
X·8Asleep on disk1 / 5

Questions

Does anything about my work come to you?

No. The free version never contacts us. A paid licence checks its key once a day, and that message holds the key, a hash of the machine and the version, nothing else. Your code, prompts, transcripts, names, costs and the features you use never come to us.

What does a paid licence do without a connection?

It keeps working for 30 days without reaching us. The check only asks whether the key is valid; nothing runs on our side.

Who sees my prompts, then?

The provider of the engine you run, as without Agent Farm: Anthropic for Claude Code, OpenAI for Codex, Google for Gemini and Antigravity, and the providers you give OpenCode. A route sends a run to the provider you picked for it.

Does Agent Farm sandbox my agents?

No. It maps its permission choices onto each engine's own: Claude Code's permission modes, Codex's sandbox, Gemini's approval mode, Antigravity's mode, OpenCode's plan agent. Parallel runs work in separate git worktrees. The guards on this page stop the commands that should not run.

Do the guards work on every engine?

They act in the hook an engine runs before a tool: Claude Code's, and Codex's. BridgeGuard reports for each engine whether a hook covers it, so an engine without one is never assumed to be guarded.

Can I let one command through?

Yes, on purpose and one command at a time: af:allow-shell for ShellGuard, af:allow-id for BridgeGuard. It is written into the command, so the session's transcript shows every time it was used.