suna

kortix-ai/suna

The AI command center for your company

20k
Stars
3.4k
Forks
12
Open issues
152
Watchers
TypeScript OtherLast pushed Jul 7, 2026

Overview

Kortix provides an integrated platform where AI agents, skills, and integrations coexist as code in a git repository. Users can manage and deploy their AI workforce using version-controlled configurations.

Categories

Tags

Similar tools

Install

npm install suna

README

Kortix

The AI command center for your company

One repo. One config. A workforce of AI agents that does the real work — and everything is code you own.

Website · Documentation · Cloud · Manifesto



Quickstart

Three commands. Build your company like a codebase, then bring it live.

# 1 · Install the CLI
curl -fsSL https://kortix.com/install | bash

# 2 · Scaffold a project — creates kortix.yaml + your agents, skills and runtime config
kortix init

# 3 · Ship it — pushes your repo and brings the whole thing live in the cloud
kortix ship

That's the loop. From here:

kortix sessions new --prompt "Summarize this week's commits and open a change request"
kortix cr ls          # review what an agent proposes — merge to keep it
kortix chat           # talk to a session's agent from your terminal

Prefer zero setup? Sign up at kortix.com, create a project, and start a session — nothing to install. Full command surface: CLI reference.


A company is going to be a git repository

Not as a metaphor — literally something you can clone. Inside it: your agents, the skills they've built up, the way the work actually gets done, every fact the company has learned, and the definition of the machines it all runs on. Versioned. Diffable. Owned outright. Running on its own around the clock, opening pull requests against itself, getting better at being your company while everyone's asleep.

Most AI tools give you a chat box. Kortix gives you a command center — one place where your agents, skills, integrations, automations and memory all live, and a workforce of agents that produces real output (decks, reports, code, replies, deployed work), not just chat. It feels as simple as a chat app. Underneath, everything is code you own.

project  (git repo + kortix.yaml)
   └─ session ──> isolated cloud sandbox on a branch named after the session
                     └─ agent (OpenCode) works, commits, pushes
                           └─ change request ──> you review & merge ──> main
  • Every session runs in its own disposable Linux sandbox on its own branch — the agent can install, run and break anything; only what it commits survives.
  • Work reaches main only through a change request you approve, so the company self-improves one reviewed change at a time.
  • Run thousands of agents in parallel on the same config, each fully isolated, each feeding work back through change requests.

What's in the command center

AgentsMarkdown personas with a scoped reach into tools — one per role or task. Installable in a click, able to rewrite themselves.
SkillsReusable know-how that encodes how your company does a job. Written once, shared into every session.
Connectors3,000+ apps in a click — plus MCP, OpenAPI, GraphQL and raw HTTP — brokered server-side through one scoped token.
SecretsEncrypted, scoped per person and group, injected into sandboxes at runtime, never exposed to the model or logs.
ChannelsSlack and chat surfaces — one click stands up a bot that starts sessions where your team already works.
TriggersCron and signed webhooks that spawn sessions automatically — every morning, or the instant something happens.
MemoryA living company brain — plain files today, a system that compounds what it learns over time.

Work runs three ways: on-demand (ask in chat, get it now), human-assisted (the agent works and checks in for the calls that matter), and automated (runs on a sc