Build an MVP in a weekend
Dispatch four agents at once — one on frontend, one on API, one on tests, one on docs. Each works on its own branch. Merge when PRs open.
Shipped in 2 days instead of 2 weeks.
Code Analysis, Git, Networking, Database, System Tools & Multi-Platform Gateway
Squan is a desktop command center that dispatches multiple AI agents to work on your codebase in parallel. Create tasks, chat with agents, and merge their work — all from one interface.
Create a task, dispatch 3 agents, watch them ship a PR.
Kanban board, agent chat, and cost dashboard — all in a native desktop window.
Drag tasks across columns or drive the flow from the sq> console.
Follow-up questions, tool-call breakdowns, mark-complete in one click.
Live per-agent cost, tokens, and runtime — no surprise bills.
Parallel agents, interactive workflows, zero friction
Ship 4x faster with concurrent workers
Follow-up questions, even after completion
Each agent gets its own git worktree
Every task change is a commit
Every agent gets instant access to filesystem ops, git commands, code analysis, networking, databases, and more — plus control your agents from any messaging platform.
15 tools
read, write, edit, list, search, tree, glob, diff, copy, move, delete, archive, checksum
12 tools
status, diff, log, branch, commit, stash, blame, cherry-pick, merge, tag, remote, reset
7 tools
symbols, references, metrics, dependencies, lint, AST, duplicates
7 tools
fetch URL, web search, HTTP, download, DNS, screenshot, port check
4 tools
SQLite query, list tables, describe, CSV query
8 tools
system info, env vars, processes, disk usage, network, kill, open URL, clipboard
Each platform adapter implements send/receive via their native API (WebSocket, long poll, webhook, SMTP/IMAP). One router manages sessions, commands, and maps platform users to Squan agents.
/new /agents /switch /status /stop /clear /models /help — work identically on every platform
Windows (signed) • macOS Intel (signed & notarized) • macOS Apple Silicon (signed & notarized)
Six core capabilities that make multi-agent development effortless.
Dispatch multiple AI agents in parallel. Each runs in an isolated git worktree — no conflicts, true concurrency.
Ask follow-up questions after an agent finishes, give more instructions, or click Mark Complete to advance the board.
Tasks flow: Open → In Progress → PR Review → Landed. Drag, drop, or drive it from the sq> console.
53 built-in tools (filesystem, git, code analysis, network, database, system, agent coordination) + 1000+ MCP servers. Pick any model: Claude, GPT-4o, Gemini, Ollama.
All project state lives in .squan/ — tasks as markdown, committed to git. Full audit trail, reviewable in PRs.
Live event stream, per-agent cost tracking, metrics dashboard. See exactly what every agent is doing and spending.
One desktop app, many agents, one git repo. Each agent gets its own worktree — branches stay clean, merges stay simple.
Three scenarios where dispatching agents in parallel beats doing it yourself.
Dispatch four agents at once — one on frontend, one on API, one on tests, one on docs. Each works on its own branch. Merge when PRs open.
Shipped in 2 days instead of 2 weeks.
Split the migration by module. Assign one agent per package to upgrade imports, rewrite deprecated APIs, and run the test suite. Review PRs as they land.
30 modules migrated in parallel, not serially.
Point tester-role agents at every untested module. Each writes unit tests, runs them, and opens a PR. You review, merge, and repeat.
From 20% to 80% coverage without a sprint.
Download Squan and start dispatching AI agents to build your projects in parallel. Chat with them, give follow-up instructions, and ship faster.