paperclipOpen-source control plane for running fleets of heterogeneous AI agents as a "company" — bring your own agent, assign goals, org charts, budgets, governance, and an audited ticket system.
Why switchSame job — run your agents as a 'company' with an org chart and task system. paperclip bets on governance (budgets, audits, tickets) for heterogeneous fleets; alook bets on email-native simplicity for solo builders running coding agents.
Full comparison → squadMulti-agent terminal collaboration for AI CLIs: a manager, workers and an inspector — Claude Code, Gemini, Codex, OpenCode — coordinating through one-shot shell commands and SQLite. No daemon.
Why switchBoth coordinate multiple local coding agents into a team; alook builds the full always-on 'AI company' (email, org charts), squad strips it to slash commands + SQLite you can hold in your head.
Full comparison → coreSelf-hosted, always-on "personal AI OS": watches your apps, keeps a persistent memory graph, and acts autonomously within guardrails — a product, not a library for building agents.
Why switchBoth are self-hosted, always-on 'AI that works for you while you sleep' products with persistent memory — core shapes it as one personal AI OS watching your apps; alook shapes it as a team of role-assigned coding agents.
Full comparison → Auto-CompanyA fully autonomous 'AI company' on your own PC: 14 expert-modeled agents ideate, decide, code, deploy and market 24/7 — driven by Claude Code or Codex CLI, with a local dashboard.
Why switchBoth stage an 'AI company' of local coding agents; alook is the collaboration layer you join (email, org charts), Auto-Company the hands-off experiment that runs the whole firm itself.
Full comparison → contrabassTerminal-first orchestrator for issue-driven AI coding-agent runs — polls Linear/GitHub, runs Codex/OpenCode in git worktrees with retries and verification. Go/Charm rebuild of OpenAI's Symphony.
Why switchBoth turn local coding agents into a coordinated team working a shared board; alook is an always-on collaboration layer (per-agent email, kanban, shared memory), Contrabass is a leaner issue-queue dispatcher with per-run verification and retries.
Full comparison → CodeNomadDesktop cockpit for OpenCode: multi-instance sessions, git worktrees, remote browser access, voice input and a command palette — a workspace for living in AI coding sessions.
Why switchBoth put a management surface over local coding agents — alook turns them into an always-on multi-agent 'AI company', CodeNomad gives one developer a rich single-cockpit for parallel OpenCode sessions.
Full comparison → FusionA multi-agent software factory: describe a task, agents plan (PROMPT.md), build, review and merge in isolated worktrees — kanban + graph board, missions, agent chat rooms, any model. Early preview.
Why switchBoth are collaboration layers that turn local coding agents into a coordinated team on a kanban board; alook leans on per-agent email and shared memory, Fusion on planned workflows, worktree isolation and merge gates.
Full comparison →