ZacharyZhang-NY e53ac36176 feat(session): auto-compact long transcripts via transformContext
pi's `transformContext` hook fired on every LLM call but returned
the transcript unchanged, so a long-running agent paid per-token
for its entire history on every turn. The README promised "sessions
persist + auto-compact" but the main loop had no compaction wired
in at all — only rotation at the long-cycle boundary.

`context-compactor` closes that gap. A pure, provider-free function
estimates tokens (~4 chars/token), short-circuits below a 120K
threshold, and on overflow keeps the last 20 messages verbatim
while collapsing older ones into a single "context summary" user
turn. The summary preserves the original task and the first twelve
assistant highlights so the agent has continuity without forwarding
every historical turn.

Compaction is non-destructive: the Agent's in-memory transcript
and the SQLite session store still hold the full history, feeding
UI timelines and audit. Only the LLM payload shrinks. Rotation
remains the long-cycle boundary (separate commit) — compaction is
what keeps each individual LLM call within budget.
2026-04-19 01:14:48 -04:00
2026-04-16 14:48:51 -04:00
2026-04-17 14:03:56 -04:00
2026-04-04 12:03:50 -04:00
2026-04-16 14:48:51 -04:00
2026-04-18 22:45:41 -04:00
2026-04-17 14:03:56 -04:00
2026-04-17 14:03:56 -04:00
2026-04-04 12:03:50 -04:00
2026-03-15 22:15:01 -04:00
2026-04-17 22:41:59 -04:00

AgentCompany logo

AgentCompany

Run an AI company from your desktop.

Latest Release License Platform Electron

Download  |  Website


AgentCompany dashboard

What it does

Type a company name and a goal. A CEO agent boots, hires specialists, forms departments, and runs the business. You approve or steer from the desktop.

Local, SQLite-backed, no external services. Inspired by Paperclip.


26 providers, no CLI

The runtime links pi-mono directly.

OAuth (5): Claude Pro/Max · ChatGPT Plus/Pro (Codex) · GitHub Copilot · Gemini CLI · Antigravity

API key (18): Anthropic · OpenAI · Google · Mistral · Groq · Cerebras · xAI · OpenRouter · Vercel AI Gateway · ZAI · OpenCode · OpenCode Go · Hugging Face · Kimi · MiniMax · MiniMax CN · Fireworks · Fireworks Firepass

Cloud (3): Azure OpenAI · AWS Bedrock · Google Vertex AI

Credentials are SecretVault-encrypted in SQLite.


Two execution modes

  • AI CEO — autonomous. Hiring, tasks, deliverables run without you.
  • AI Co-Founder — pauses at hire_agent / document_review / plan_review / strategy_review for your decision.

Switch at Settings → Execution mode.


Features

Self-organizing teams

CEO builds the org chart from one goal.

Org chart

Agent messaging

Threads and DMs between agents. Messages land in each recipient's transcript as pi AgentMessage turns.

Agent messaging

Tasks

Goals break into tasks. Agents pick them up, report progress, escalate blockers.

Task queue

Approvals

Hiring, deliverables, plan/scope/strategy reviews, budget overrides, production deploys pause for the board.

Approvals

Documents

Plans, strategies, and specs in a shared center, linked to the tasks that produced them.

Document center

Launch in a minute

Name, mission, goal, provider, mode.

Onboarding


Quick Start

Download the latest release — macOS (Apple Silicon & Intel), Windows, Linux.

Build from source

# Node.js 22+, pnpm 10+
pnpm install
pnpm dev

First run

  1. Onboarding probes your shell PATH for node (agents call the local HTTP API via node -e).
  2. Settings → Providers. Sign in or drop a key.
  3. Create a company: name, mission, goal, mode, workspace.

Verification

pnpm typecheck
pnpm lint
pnpm test:unit
pnpm test:integration
pnpm test:e2e
pnpm build:verify

Packaging

pnpm build         # Package for current platform → /build/release
pnpm build:dir     # Unpackaged directory
pnpm build:current # Current host platform
pnpm release:local # Signed release pipeline — see docs/release/local-r2.md

Targets: macOS .dmg, Windows .exe (NSIS), Linux .AppImage. Built with electron-builder. Local builds use ad-hoc signing (CSC_IDENTITY_AUTO_DISCOVERY=false). Defaults to --publish never.


Architecture

src/
  main/
    agent-runtime/       RuntimeBridge, SqliteSessionStore, CostWriter
    credentials/         CredentialStore, Resolver, OAuthLoginService
    api-server/          Agent HTTP API
    orchestration/       Scheduler, run dispatch
    prompt-builder/      System prompt assembly
    thread-integration/  Thread runtime event routing
    worker/              utilityProcess worker — direct new Agent(...)
    database/            SQLite schema + migrations
  preload/             Typed DesktopApi via contextBridge
  renderer/            React 19 UI
  shared/              Zod schemas shared across processes
  • SQLite local; no external services.
  • contextIsolation: true, nodeIntegration: false, Zod-validated IPC.
  • Worker constructs new Agent({...}) from @mariozechner/pi-agent-core directly.
  • Sessions persist as session_entries; auto-compact via shouldCompact / compact.
  • Thread runtime (conversation_threads / conversation_events / thread_wait_states) sits above pi's AgentMessage stream.

Tech Stack

Layer Tech
Framework Electron 39.8.0
Language TypeScript 5.9
UI React 19, Tailwind CSS 4, Framer Motion, Zustand
Build electron-vite, Vite 7, electron-builder
Database SQLite via node:sqlite (WAL)
Validation Zod 4
Agent runtime @mariozechner/pi-ai, @mariozechner/pi-agent-core, @mariozechner/pi-coding-agent
Testing Vitest, Playwright

License

MIT

S
Description
No description provided
Readme MIT
135 MiB
0 Stars 1 Watchers 0 Forks
2026-10-10 01:31:40 +00:00
Languages
TypeScript 93.7%
Shell 3%
CSS 2.3%
Python 0.5%
JavaScript 0.4%