A software company of AI agents, on your own computer

Newv1.4.1 is out

Give one goal. The CEO splits it into tasks, department leads do the work in real coding terminals, QA reviews the diff, rules are enforced by code, and an evidence-backed report lands in an Obsidian vault you can open yourself.

Works with the tools and backends you already use

Claude Code Codex CLI OpenCode Gemini CLI Abacus.AI CLI Aider Anthropic API OpenRouter Kimi GLM MiniMax NVIDIA NIM Ollama

How it works

From goal to report

  1. Claude Code, Codex, OpenCode, Gemini CLI or Aider on PATH. Log them into your subscription or add API keys in Settings → Backends.

  2. A template staffs management, software, design, research, QA, marketing, client relations, finance, operations and administration — or start empty and let the CEO hire.

  3. The secretary carries it to the CEO. The CEO writes a plan with acceptance criteria per task; in Co-Founder mode it waits for your approval.

  4. Leads work in a shared project repository. Click anyone to look over their shoulder, message them, or read what they wrote to each other.

  5. QA reviews the diff, the rule engine checks paths, dependencies and commands, and a report with real evidence is filed in the vault and committed to git.

  6. Everyone remembers: daily notes, lessons, decisions. After a restart the terminals you opened yourself come back with the tool's continue flag, and orchestrated work is re-dispatched with its brief.

Orchestration

The conductor leads, the choir stays on key

The general manager hands out every job by how hard it is. Each employee works with the right model, at the right effort, in its own files - nobody sings over anyone else.

  • Defined subagents

    Claude Code employees can open subagents to go faster, but only the company's three: explorer (read only), implementer and verifier. Company policy sets their model and effort, never above the employee's own model.

  • Model and effort by difficulty

    The plan stamps every job easy, medium or hard. Easy work opens on Sonnet at low effort, hard work on Opus at high effort: simple jobs don't burn the expensive model, hard ones don't stall on a weak one.

  • Critical roles on the top model

    The general manager, department leads and reviewers run on the strongest model by default. Moving one to a weaker model asks for your approval.

  • The QA team tests it

    When the jobs are done, QA tests the combined result; every bug becomes its own fix job and nobody reviews their own work. On big jobs a refuter subagent challenges each finding, and only the ones that stand reach you.

  • Limit brake

    The 5-hour and weekly windows of the Claude subscription are watched separately. As one fills the company slows down, at the limit it stops, and it carries on by itself when the window resets.

  • No work gets lost

    A quiet employee gets a status check from its lead, and a stuck session reopens where it left off. Unsaved work is snapshotted every 10 minutes, and git commands that would wipe someone else's work are blocked.

  • Every file has an owner

    Employees announce the files they work on, and parallel subagents never share files. An unknown file is not deleted; its owner is asked first, and you when nobody owns it.

  • Queued messaging

    Messages travel through a background queue; when an employee's terminal is closed, its messages are delivered as soon as it opens. Claude employees message each other through Claude's own messaging, and it all shows up on the Messages page.

The platform

Everything a company needs, without leaving your machine

One goal in — an org that plans itself, works in the open, remembers, and holds its own budget.

Real terminals, not prompts

Every employee is a live Claude Code, Codex, OpenCode, Gemini CLI or Aider session in its own sandboxed folder. Open several side by side, type into them, interrupt them.

Self-organizing

The CEO plans, hands tasks to department leads, hires missing specialists and opens departments when the mission needs them.

Memory in Obsidian

Profiles, daily logs, lessons, decisions and reports are Markdown notes with wikilinks. You can read and edit them; retrieval costs zero tokens.

Rules enforced by code

Your decisions become policies checked against the real diff and the commands that ran. Violations send work back with the violation listed.

Evidence, not claims

Reports carry the diff, raw command output, the rationale (why this path, what was rejected), review verdict and cost.

AI CEO or Co-Founder

Fully autonomous, or human in the loop: plans, deliveries and hires wait in your approval queue with a note back to the employee.

Messages

Direct conversations and department channels. Orchestration is narrated as messages; agents can message each other and you.

Budget you control

The local gateway measures every call per employee from the provider's own counters. Monthly and per-person caps stop dispatch, not running work.

Connectors

GitHub, Slack, Notion, Linear, Supabase, Stripe, Sentry, Playwright and more via MCP — one catalog, secrets kept in the key store, written into every tool's own format.

An office you can read

Walking, speech bubbles and status come from real events. Rooms and buildings are editable. Positions are simulated on the server, so every screen sees the same office.

Key pool with failover

Several keys per backend; on 429 the gateway moves to the next, on 401 it retires the key. Tools never see real keys.

Phone and remote

LAN access with a PIN, one-click Cloudflare tunnel, single-pane mobile layout. Turkish and English.

0online right now

0terminals running

45downloads

Why this one

Built for people who want to see the work

Most multi-agent tools are a black box: eight agents run, one gets stuck, nothing is remembered. Agentic Company makes the company observable, accountable and persistent.

Agentic CompanyTypical agent frameworks
AgentsReal CLI terminals you can open and type intoAPI loops behind a chat window
MemoryObsidian vault, human-readable, git-friendlyVector store or nothing
RulesDeterministic checks on the real diff and commandsA line in the system prompt
ReportsDiff, raw output, rationale, review, costThe model's summary of itself
CostMeasured per employee at the gateway; capsWhatever the bill says
KeysPool with failover, encrypted at rest, never shown to toolsOne key in an env var
DeploymentOne binary, no runtime, everything on your machineNode/Python stack, cloud login

Pricing

Free to run. Pay only for what you want more of.

The app is a single binary that runs on your machine; you pay your AI provider directly. Paid plans unlock scale, remote access and team features. No usage-based fees from us, ever.

Free

$0forever
Download
Companies
1
Departments per company
Unlimited
Employees per company
8
Employees working at once
8
Remote access
Not included
All tools and backends, your own keys or subscription
Office, board, memory vault, rules, reports
Messages, approvals, budget caps
LAN access with PIN

ProMost popular

$4.99per month
Talk to us

For now plans are bought in the mobile app only. Want one right away? Write to us.

Companies
3
Departments per company
15
Employees per company
80
Employees working at once
80
Remote access
Included
Connector catalog (GitHub, Slack, Notion, Linear, Stripe…)
CEO self-staffing and multi-building offices
Priority updates and email support

Team

$19.99per month
5 seats · $4/seat
Talk to us

For now plans are bought in the mobile app only. Want one right away? Write to us.

Companies
Unlimited
Departments per company
Unlimited
Employees per company
Unlimited
Employees working at once
Unlimited
Seats
5
Remote access
Included
Everything in Pro
Several people in the same company, per-user approvals
Shared key pool with per-company budgets
Audit log of every decision and delivery
Self-hosted license server, SSO on request

Prices are per install, billed monthly, cancel anytime. Local-first stays true on every plan: nothing about your company leaves your machine, including on Team. Model usage is billed by your provider, not by us. Refund Policy · Terms of Service · Privacy Policy

Download

Install the build for your machine

Single binary. No installer, no runtime. Data stays in your user profile.

Windows

x64 · arm64

Run agentic-company.exe; it prints the address and a PIN and opens a window.

Get for Windows

macOS

Apple Silicon · Intel

Unzip and open Agentic Company.app, or run the binary.

Get for macOS

Linux

x64 · arm64, statically linked

install-linux.sh adds a desktop entry.

Get for Linux

Mobile app

Your company in your pocket: remote access through the tunnel, notifications, team and plan management. Works alongside the desktop app.

agentic-company --port 7777          # LAN access with a PIN
agentic-company --tls-cert c.pem --tls-key k.pem
agentic-company --backup C:\backups\ac.zip

FAQ

Frequently asked questions

How to use

Does my data or code leave my machine?

No. Everything lives under your data directory: company config, the Obsidian vault, a SQLite database, project repositories and workspaces. The only network traffic is your coding tools calling the AI provider you connect (through a local gateway that injects the keys) and signing in with your account. If you use dictation, your voice is turned into text on Chrome's or Edge's own servers.

Which AI runtimes work?

Tools: Claude Code, Codex CLI, OpenCode, Gemini CLI, Abacus.AI CLI, Aider. Backends: your subscription login, Anthropic API, Google Gemini API, OpenRouter, NVIDIA NIM, Kimi, GLM, MiniMax, any OpenAI-compatible endpoint, or a local Ollama. Tool and backend are chosen per employee.

How does the CEO work?

A goal becomes a plan task for the CEO. The plan lists tasks with department, brief and acceptance criteria — and, when the current team cannot cover the work, new hires. Tasks go to department leads, deliveries go to a reviewer, reports are filed. In Co-Founder mode the plan, every delivery and every hire wait for your approval.

What does it cost to run?

The app is free. You pay your AI provider. Employees on a subscription login cost nothing extra; API-backed employees are measured per call at the gateway, with monthly and per-person caps.

Can I use it from my phone?

Yes. Open the printed LAN address and enter the PIN, or start the Cloudflare tunnel from Settings for a temporary https address. The layout switches to single-pane tabs on narrow screens.

Is it secure enough to expose?

PIN login with rate limiting, same-origin checks on every write, strict Content-Security-Policy, loopback-only gateway, secrets encrypted at rest on Windows and redacted from reports. The operations runbook that ships with the app documents the full model.

Build your own software company