Private beta — orchestrate your coding agents

One calm cockpit for a swarm of agents.

SupraSpace turns a tangle of terminal windows into a single living command center — launch, watch, and steer many coding CLI agents at once, each with its own task, memory, and live terminal.

Join the waitlist See what it does

Lightweight · works with Claude Code, Codex, OpenCode & any CLI · runs anywhere Node does

supraspace.app

api-gateway

Search projects, tasks, sessions…

Dashboard

4 active sessions

Backlog

Ready

Running

Blocked

Review

126

Done

Refactor auth router

Refactoring Specialist · Claude Code

Running

Elapsed 04:12

Last out 0:03

✓ extracted middleware chain
› applying edit 2/3 …

OpenStopReviewDone

Add rate limiting

Code Reviewer · Codex

Waiting

Elapsed 01:48

Last out 1:12

? Apply suggested limiter to /login? (y/n)

OpenStopReviewDone

Migrate to Postgres 16

Postgres Pro · Custom

Idle

Elapsed 12:30

Last out 3:40

› EXPLAIN ANALYZE complete · 0 seq scans

OpenStopReviewDone

Board

api-gateway · 18 tasks

Backlog3

Document webhook payloads

Technical Writer

Audit dependency tree

Security Auditor

Ready2

Add OpenAPI schema

API Designer

Running4

Refactor auth router

Refactoring Spec.

Migrate to PG 16

Postgres Pro

Blocked1

Wire payment webhook

Payment Integ.

Review2

Add rate limiting

Code Reviewer

Done6

Cache layer for /search

Performance Eng.

Sessions

2 × 2 grid · 4 live

Running

Refactor auth router

Refactoring Specialist · Claude Code

api ❯ claude --agent refactorer

› loading .supraspace/ memory …

✓ context loaded · 6 files

› analyzing router.ts

Waiting

Add rate limiting

Code Reviewer · Codex

api ❯ codex review --diff

✓ scanned 14 files

⚠ suggest limiter on /login

? apply fix? (y/n)

Running

Migrate to Postgres 16

Postgres Pro · Custom

api ❯ psql -f migrate.sql

› ALTER TABLE sessions …

✓ 4 migrations applied

› reindexing

Running

Write integration tests

Test Automator · OpenCode

api ❯ opencode --agent test

› generating cases …

✓ 42 passing

› coverage 91%

Memory

space map · 6 files

Project Memory

architecture.md

decisions.md

agent-notes.md

tasks.md

Fastify + Drizzle

SQLite store

node-pty / ConPTY

argv, not shell

append-only logs

MCP & Integrations

connected

MCP servers

filesystemstdio · local

ready

fetchhttp · remote

ready

postgresstdio · local

ready

Integrations

GitHubSource control

connected

VercelHosting

connected

CloudflareInfrastructure

connected

Agents

38 profiles

Refactoring Specialist

Code refactoring expert

Improves structure without changing behavior, tests green.

Security Auditor

Vulnerability expert

Audits for injection, auth gaps & secret leakage with fixes.

API Designer

REST & GraphQL design

Clean, consistent contracts with proper status codes.

Test Automator

Test framework expert

Robust unit / integration / e2e suites without flakiness.

Postgres Pro

PostgreSQL expert

Schema design, indexing & query optimization.

Agent Organizer

Multi-agent coordinator

Splits a goal into tasks & routes them to the right agents.

Bring your own CLI

Works with every coding CLI you already love.

SupraSpace doesn't lock you into one model or vendor. Point it at any interactive coding CLI — it spawns a real terminal, injects your prompt, and streams the output. Mix and match agents across tools in the same workspace.

Claude Code

claude --agent <profile>

Anthropic's agentic CLI runs natively — your task, memory, and skills load on boot.

Codex

codex --prompt <task>

OpenAI's coding CLI plugs straight in with clean prompt-flag injection.

OpenCode

opencode --agent <profile>

First-class support, including agent import from your opencode.json.

Any CLI

your-tool {{prompt}}

Define a command template once and SupraSpace drives any interactive CLI you use.

Configurable prompt injection — stdin, args, file context, or prompt flag — so each tool gets your task exactly the way it expects it.

Drives any CLI · plugs into your stack

Why teams reach for it

Built for running many agents, not babysitting one.

Most tools give you a single chat box. SupraSpace gives you a control room: parallel sessions, a board that mirrors real progress, memory the agents actually read, and status you can trust — without leaving your machine.

Run agents in parallel

Launch a whole crew at once and watch them in a 1, 2, 4, or 6-up terminal grid. Each agent gets its own task, profile, and live PTY — no more juggling a dozen terminal tabs.

Status you can trust

No spinner that lies. Status comes from real process liveness, output recency, and your own patterns — so running means running and waiting means it needs you.

Lightweight by design

A single Fastify process and an embedded SQLite file — light enough to sit quietly beside your editor. It streams output event-driven and idles when your agents do, so it barely registers on your machine.

Memory the agents read

Plain Markdown notes — architecture, decisions, agent notes — live beside your code and get woven into every launch prompt. Explore it as an interactive space map.

MCP & Skills, built in

Register local or remote Model Context Protocol servers, manage reusable skill modules, and export a CLI-ready config — give every agent the same superpowers.

Runs anywhere

Works on Windows, macOS, and Linux — same terminal engine, same data paths. Drive it locally on your laptop or behind a reverse proxy on a VPS. Your call.

SupraSpace

One conductor, many players

From a single task to a coordinated crew.

Plant the task

Drop a task on the board, pick an agent profile from 38+ specialists, and SupraSpace assembles the launch prompt from your task and project memory.

Launch in parallel

Fire off several agents across one or many projects. Each runs in its own real terminal — no shared state, no stepping on each other.

Watch & steer

The dashboard flags whoever needs you. Jump into any session, type a reply, then review the diff, git status, and transcript before marking it done.

Kanban board

A board that tells the truth.

Drag a task and its agent follows. When a session starts the card flips to running on its own; when an agent finishes, it lands in review. The board is a live mirror of what your agents are actually doing.

Drag-and-drop across backlog → ready → running → review → done
Quick-launch an agent straight from a card
Status updates flow back from real session lifecycle

Running

Refactor auth router

Migrate to PG 16

Review

Add rate limiting

Done

Cache /search

Fix flaky test

Live terminals

Real terminals, streamed live.

Every session is a genuine PTY streamed to your browser with xterm.js. Read-only previews keep the grid calm; pop any session out for a full interactive terminal with scrollback, keyboard, and links.

1 / 2 / 4 / 6-panel layouts that keep live connections
Type back the moment an agent waits for input
Append-only transcripts survive every restart

api ❯ claude --agent refactorer

› loading project memory from .supraspace/ …

✓ context loaded · 6 files · 2 decisions

› extracting middleware chain

✓ refactor plan ready · 3 edits

› applying edit 1/3

Project memory

Context that compounds.

Six plain-Markdown files per project capture architecture, decisions, and agent notes — versioned with your code, editable by you, and injected into every launch. See it as an explorable concept map of everything your agents know.

Transparent Markdown — no hidden vector black box
Pick which snippets ride along on each launch
Interactive space-map view of the whole project

Memory

architecture.md

decisions.md

agent-notes.md

tasks.md

6-up

Terminals at a glance

38+

Specialist agent profiles

Platform integrations

Tiny process, big reach

Connect your world

Your agents reach the tools you already use.

Connect a provider once and your agents can act through it. Credentials stay on your machine and only ever travel to each provider's own API — every connection is verified before it's trusted.