docs(readme): rewrite for pi-mono runtime + 26-provider matrix + execution modes

The previous README described an app that no longer exists:

- Listed "Claude Code / Codex CLI / Gemini CLI" as the supported runtimes
  — all three were removed from the app months ago; pi-mono replaced
  them as the sole agent runtime (commit 4de9cd0 + 60178ce).
- Advertised `packages/adapter-utils` + three adapter packages under
  `packages/` — that directory was deleted.
- Carried a "PLEASE USE A CODING PLAN" warning that predated OAuth
  subscription support; five subscription providers (Claude Pro, ChatGPT
  Codex, Copilot, Gemini CLI, Antigravity) are now first-class.
- Made no mention of the 26-provider catalog, the AI CEO vs
  AI Co-Founder execution modes, the encrypted credential vault, the
  thread runtime, or any of the architecture that has become the app.
- Promised "I will add support for Ollama and Github Copilot" — Copilot
  has shipped for months.

New README covers what the app actually is today:

- Pi-mono as the one runtime, linked as a direct npm dependency.
- 26 providers in total: 5 OAuth subscriptions + 18 API-key providers
  + 3 cloud providers — counts verified against the on-disk catalog
  files (connector-definitions-data-{oauth,apikey,cloud}.ts).
- Two execution modes (AI CEO, AI Co-Founder), per-company, with the
  specific approval types listed for Co-Founder mode's review gates.
- Encrypted credential storage (SecretVault-backed SQLite) instead of
  plaintext env files or pi's default ~/.pi/agent/auth.json.
- Real agent-to-agent messaging layered on pi's AgentMessage stream
  via the thread runtime.
- Architecture tree updated: `packages/` gone, main-process subtrees
  (agent-runtime / credentials / api-server / orchestration / worker /
  thread-integration / database) named explicitly.
- First-run flow that accurately describes what onboarding does —
  including the real Node-in-PATH probe (commit ab731e6) agents need
  for HTTP callbacks.
- Tech stack row for pi-mono packages added.

Kept intact: screenshots, download/build/verify/packaging commands,
licence. Badges updated to match the cross-platform targets currently
shipping.

Deleted: the "Supported AI Runtimes" table (obsolete), the coding-plan
token warning (obsolete), the future-plans line (Copilot already
shipped, Ollama not on the roadmap).

Language pass: Jobs-style tightening of the "What it does" paragraph
and section openers; subtitle changed from "Launch autonomous AI
companies..." to "Run an AI company from your desktop." — shorter,
more direct, stops selling and starts describing.
This commit is contained in:
ZacharyZhang-NY committed 2026-04-17 21:50:08 -04:00
1 parent b68307b24f
commit ff7d1e68a1
1 file changed
+79 -48
+79 -48
View File
@@ -5,10 +5,8 @@
<h1 align="center">AgentCompany</h1> <h1 align="center">AgentCompany</h1>
<p align="center"> <p align="center">
<strong>Launch autonomous AI companies from your desktop.</strong><br/> <strong>Run an AI company from your desktop.</strong><br/>
Set a goal. Watch AI agents self-organize, delegate, and deliver.<br/> Give it a mission. Watch agents hire, delegate, and deliver.
<strong>PLEASE USE A CODING PLAN, IT COMSUMES A LOT OF TOKENS</strong><br/>
I will add support for Ollama and Github Copilot in the near future.
</p> </p>
<p align="center"> <p align="center">
@@ -19,7 +17,7 @@
</p> </p>
<p align="center"> <p align="center">
<a href="https://github.com/ZacharyZhang-NY/AgentCompany/releases">Download</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://agentcompany.pages.dev">Website</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="#features">Features</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="#quick-start">Quick Start</a> <a href="https://github.com/ZacharyZhang-NY/AgentCompany/releases">Download</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://agentcompany.pages.dev">Website</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="#what-is-agentcompany">What it does</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="#quick-start">Quick Start</a>
</p> </p>
--- ---
@@ -30,57 +28,79 @@
## What is AgentCompany? ## What is AgentCompany?
AgentCompany is a cross-platform desktop app that turns a single goal into a coordinated AI team. You provide a company name, description, and mission. A CEO agent self-organizes departments, delegates tasks, and produces deliverables — code, content, research, business plans, and more — while you observe and approve through a chat-based command hub. Inspired by **[Paperclip](https://github.com/paperclipai/paperclip)** You type a company name, a mission, and a first goal. AgentCompany boots a CEO agent who hires specialists, forms departments, and runs the business — writing code, drafting plans, producing research, shipping deliverables. You watch, approve, and steer through a desktop command center.
### Supported AI Runtimes Local-first. No external services. Your data stays on your machine.
| Runtime | Status | Inspired by **[Paperclip](https://github.com/paperclipai/paperclip)**.
|---------|--------|
| Claude Code | Ready | ---
| Codex CLI | Ready |
| Gemini CLI | Ready | ## What's in the box
### 26 AI providers, one install
No CLIs to install on your PATH. No `claude` / `codex` / `gemini` binaries. The agent runtime is linked directly via [pi-mono](https://github.com/mariozechner/pi).
**5 OAuth subscriptions** — sign in with the accounts you already pay for:
Claude Pro / Max · ChatGPT Plus / Pro (Codex) · GitHub Copilot · Google Gemini CLI · Google Antigravity
**18 API-key providers:**
Anthropic · OpenAI · Google Gemini · Mistral · Groq · Cerebras · xAI · OpenRouter · Vercel AI Gateway · ZAI · OpenCode · OpenCode Go · Hugging Face · Kimi For Coding · MiniMax · MiniMax CN · Fireworks · Fireworks Firepass
**3 Cloud providers:**
Azure OpenAI (Responses API) · AWS Bedrock · Google Vertex AI
Credentials are stored encrypted at rest in a SecretVault-backed SQLite table. No plaintext, no `~/.pi/agent/auth.json`, no scattered env files.
### Two execution modes, per company
- **AI CEO** — fully autonomous. Hiring, task assignment, and deliverable publishing run without you.
- **AI Co-Founder** — human-reviewed. Hiring and deliverables pause for your decision at `hire_agent` / `document_review` / `plan_review` / `strategy_review` approval gates.
Switch any time in Settings → Execution mode.
--- ---
## Features ## Features
### Self-Organizing Teams ### Self-organizing teams
Your AI CEO builds the org chart — recruiting specialists, creating departments, and establishing reporting lines from a single goal. Your AI CEO draws the org chart — recruiting specialists, creating departments, and establishing reporting lines from a single goal.
<p align="center"> <p align="center">
<img src="screenshots/Auto-OrgChart-Team.jpeg" width="700" alt="Auto-generated org chart with CEO and department heads" /> <img src="screenshots/Auto-OrgChart-Team.jpeg" width="700" alt="Auto-generated org chart with CEO and department heads" />
</p> </p>
### Real-Time Agent Communication ### Real agent-to-agent messaging
Agents coordinate through channel and direct-message threads. Watch decisions unfold in real time. Agents coordinate through channel and direct threads — not scripted status updates. Inter-agent messages feed into each recipient's conversation transcript as first-class turns, so context travels with the work instead of being re-rendered from scratch every run.
<p align="center"> <p align="center">
<img src="screenshots/AI-Internal-Realtime-Message.jpeg" width="700" alt="Real-time messaging between AI agents" /> <img src="screenshots/AI-Internal-Realtime-Message.jpeg" width="700" alt="Real-time messaging between AI agents" />
</p> </p>
### Autonomous Task Management ### Autonomous task management
Goals break down into tasks automatically. Agents pick up work, report progress, and escalate blockers without intervention. Goals break into tasks. Agents pick them up, report progress, and escalate blockers on their own.
<p align="center"> <p align="center">
<img src="screenshots/Auto-Task.jpeg" width="700" alt="Autonomous task queue with goals and status tracking" /> <img src="screenshots/Auto-Task.jpeg" width="700" alt="Autonomous task queue with goals and status tracking" />
</p> </p>
### Human-in-the-Loop Approvals ### Human-in-the-loop approvals
Critical decisions surface for your review. Approve, reject, or redirect — your company respects the chain of command. Material decisions surface to the board: hiring, document delivery, plan and scope reviews, strategy reviews, budget overrides, production deploys. Approve, reject, or ask for a revision — the company respects the chain of command.
<p align="center"> <p align="center">
<img src="screenshots/Approval-by-Human.jpeg" width="700" alt="Human approval workflow for agent decisions" /> <img src="screenshots/Approval-by-Human.jpeg" width="700" alt="Human approval workflow for agent decisions" />
</p> </p>
### AI Document Generation ### AI document generation
Agents draft business plans, marketing strategies, and technical specs — stored in a shared document center. Agents draft business plans, marketing strategies, and technical specs — kept in a shared document center linked to the tasks that produced them.
<p align="center"> <p align="center">
<img src="screenshots/Document-Center.jpeg" width="700" alt="Document center with AI-generated deliverables" /> <img src="screenshots/Document-Center.jpeg" width="700" alt="Document center with AI-generated deliverables" />
</p> </p>
### One-Click Company Creation ### One-minute company creation
Name it, describe the mission, connect a runtime, and launch. Agents start working in under a minute. Name it, write the mission, pick a provider, choose the mode, launch. Agents are at work before your coffee.
<p align="center"> <p align="center">
<img src="screenshots/Onboarding.jpeg" width="700" alt="Company creation onboarding flow" /> <img src="screenshots/Onboarding.jpeg" width="700" alt="Company creation onboarding flow" />
@@ -92,13 +112,11 @@ Name it, describe the mission, connect a runtime, and launch. Agents start worki
### Download ### Download
Grab the latest release for your platform:
**[Download AgentCompany](https://github.com/ZacharyZhang-NY/AgentCompany/releases)** **[Download AgentCompany](https://github.com/ZacharyZhang-NY/AgentCompany/releases)**
> Available for macOS (Apple Silicon & Intel), Windows, and Linux. macOS (Apple Silicon & Intel), Windows, Linux.
### Build from Source ### Build from source
```sh ```sh
# Prerequisites: Node.js 22+, pnpm 10+ # Prerequisites: Node.js 22+, pnpm 10+
@@ -106,6 +124,13 @@ pnpm install
pnpm dev pnpm dev
``` ```
### First run
1. **Launch.** Onboarding probes your shell PATH for `node` — agents invoke the local HTTP API through `node -e`, so a shell Node is required. Platform-specific install commands are shown if it's missing.
2. **Configure a provider.** Settings → Providers. OAuth providers open your default browser; API-key providers take a key; Azure/Bedrock/Vertex take their respective endpoint + credential config.
3. **Create a company.** Name, mission, first goal, execution mode, workspace path.
4. **Go.** The CEO starts within seconds.
--- ---
## Verification ## Verification
@@ -124,15 +149,15 @@ pnpm build:verify
```sh ```sh
pnpm build # Compile + package for current platform → /build/release pnpm build # Compile + package for current platform → /build/release
pnpm build:dir # Compile + unpackaged directory pnpm build:dir # Compile + unpackaged directory
pnpm build:current # Build for current host platform (see note below for other OS) pnpm build:current # Build for current host platform
pnpm release:local # Signed/uploading release pipeline (see docs/release/local-r2.md) pnpm release:local # Signed / upload release pipeline (see docs/release/local-r2.md)
``` ```
- **Targets:** macOS (`.dmg`), Windows (`.exe` / NSIS), Linux (`.AppImage`) - **Targets:** macOS (`.dmg`), Windows (`.exe` / NSIS), Linux (`.AppImage`)
- Packaging uses `electron-builder` - Packaging via `electron-builder`
- Local builds use ad-hoc signing (`CSC_IDENTITY_AUTO_DISCOVERY=false`) - Local builds use ad-hoc signing (`CSC_IDENTITY_AUTO_DISCOVERY=false`)
- Defaults to `--publish never`; override with `AGENTCOMPANY_ELECTRON_PUBLISH` - Defaults to `--publish never`; override with `AGENTCOMPANY_ELECTRON_PUBLISH`
- Cloudflare R2 release hosting + auto-update pipeline: `docs/release/local-r2.md` - Cloudflare R2 release hosting + auto-update: `docs/release/local-r2.md`
--- ---
@@ -140,22 +165,27 @@ pnpm release:local # Signed/uploading release pipeline (see docs/release/local-r
``` ```
src/ src/
main/ # Electron main process — database, services, IPC, orchestration main/ # Electron main process
preload/ # Context-isolated bridge — DesktopApi via contextBridge agent-runtime/ # RuntimeBridge, SqliteSessionStore, CostWriter
renderer/ # React 19 UI — components, hooks, i18n credentials/ # CredentialStore, CredentialResolver, OAuthLoginService
shared/ # Contracts, types, Zod schemas shared across processes api-server/ # Agent-facing HTTP API (tasks, messages, approvals, ...)
packages/ orchestration/ # Scheduler, run dispatch, turn context
adapter-utils/ # Shared adapter utilities prompt-builder/ # System prompt assembly + API docs injection
adapter-claude-local/ thread-integration/ # Thread runtime event routing
adapter-codex-local/ worker/ # utilityProcess worker — direct `new Agent(...)` via pi-mono
adapter-gemini-local/ database/ # SQLite schema + migrations
preload/ # Context-isolated bridge — typed DesktopApi via contextBridge
renderer/ # React 19 UI — components, hooks, i18n, state
shared/ # Contracts, types, Zod schemas shared across processes
``` ```
### Key Design Decisions ### Key design decisions
- **Local-first:** SQLite database, secrets in OS keychain, no external services required - **Local-first.** SQLite on your machine. SecretVault-encrypted credentials. No external services required for core operation.
- **Security:** `contextIsolation: true`, `nodeIntegration: false`, Zod-validated IPC, JWT agent tokens - **Process isolation.** `contextIsolation: true`, `nodeIntegration: false`, Zod-validated IPC. Renderer never imports `@mariozechner/pi-*`; all agent traffic is proxied through main → utilityProcess worker.
- **Agent coordination:** Agents delegate tasks, escalate blockers, and produce deliverables through the orchestration runtime - **Runtime direct.** `@mariozechner/pi-agent-core` is a first-class dependency. The worker calls `new Agent({...})` directly — no adapter shim, no CLI shell-out.
- **Session as transcript.** Each agent's conversation persists as `session_entries` rows of pi `AgentMessage[]`. Long sessions auto-compact via `shouldCompact` + `compact` from pi-coding-agent; state survives app restarts.
- **Thread runtime.** `conversation_threads` + `conversation_events` + `thread_wait_states` sit above pi's `AgentMessage` stream so the inbox / approval / review UX is a first-class runtime concern, not UI-only veneer.
--- ---
@@ -164,12 +194,13 @@ packages/
| Layer | Technology | | Layer | Technology |
|-------|-----------| |-------|-----------|
| Framework | Electron 39.8.0 | | Framework | Electron 39.8.0 |
| Runtime | Node.js 22+ | | Runtime | Node.js 22+ (bundled in Electron; shell `node` required for agent HTTP callbacks) |
| Language | TypeScript 5.9 (strict) | | Language | TypeScript 5.9 (strict) |
| UI | React 19, Tailwind CSS 4, Framer Motion | | UI | React 19, Tailwind CSS 4, Framer Motion, Zustand |
| Build | electron-vite, Vite 7, electron-builder | | Build | electron-vite, Vite 7, electron-builder |
| Database | SQLite (WAL mode, schema in `src/main/database/`) | | Database | SQLite via `node:sqlite` (WAL mode) |
| Validation | Zod 4 | | Validation | Zod 4 |
| Agent runtime | `@mariozechner/pi-ai`, `@mariozechner/pi-agent-core`, `@mariozechner/pi-coding-agent` |
| Testing | Vitest, Playwright | | Testing | Vitest, Playwright |
--- ---