Kortix 发布开源 AI 操作系统 Suna,把公司智能体配置放进一个 git 仓库
kortix-ai/suna
Kortix 发布开源 AI 操作系统 Suna,智能体、技能、公司记忆和连接器都存放在一个 git 仓库中,可版本化、可 diff、全公司共享。每个会话运行在独立的云端 Linux 沙箱和自己的分支上,产出通过变更请求由人工审核合并,支持任意模型供应商和自有 API key,可自托管或使用 Kortix Cloud 托管,托管版为 $40/seat/mo 加用量计费。
Agents that deliver finished work — reports, decks, code, replies, deployed changes — are now a product category. Every version of it runs inside a model lab, on that lab's model, with your company's brain on their side of the wall.
Kortix is the one you own. It's an open-source AI Operating System: your agents, the skills they share, your company memory, and every connector live in one git repo — versioned, diffable, and shared by the whole company. The agents work on real cloud computers — an isolated sandbox per session, on its own branch — and land what they produce through a change request a human approves.
Any model, your own API keys, your own infrastructure or our managed cloud.
Kortix is right for you if
- ✅ You want an open-source, self-hosted alternative to Claude Cowork or ChatGPT Work for your whole team → details
- ✅ You want AI agents in Slack or Microsoft Teams that use your tools and reply in the thread → details
- ✅ You want background coding agents in the cloud: a sandbox and a branch per task, and a change request you review → details
- ✅ You want to replace Zapier-style automations with AI agents that run on a schedule or a webhook → details
- ✅ You want an "AI employee" that does the work and waits for a person's approval before it acts → details
- ✅ Your security team needs governed agents: per-tool rules, approval gates, an audit trail, SAML SSO, your own VPC → details
- ✅ You want an AI Operating System to run a company with agents: every agent, skill, memory file and connector in one git repo → details
Kortix is probably not the right fit if you want a visual flowchart of fixed steps (a workflow builder such as n8n does that well), or only a chat window over your documents (Onyx, Open WebUI or LibreChat).
How it compares
| Claude Cowork | ChatGPT Work | Kortix | |
|---|---|---|---|
| Source | Closed | Closed | Open source — read it, fork it, audit it |
| Models | Anthropic only | GPT-5.6 only | Any provider, your own API keys |
| Where it runs | Anthropic's cloud, or Bedrock / Google Cloud / Microsoft Foundry — no self-host | OpenAI's cloud, no self-host | Our cloud, your VPC, or your own on-prem network |
| Your configuration | In their product | In their product | Files in a git repo you own |
| Access | Paid plans (Pro, Max, Team, Enterprise) | Paid plans, usage-metered | Self-host free · managed cloud $40/seat/mo + usage |
Competitor rows reflect publicly documented behavior as of July 2026.
Kortix and other open-source tools
| If you are looking at… | Pick it when | Pick Kortix when |
|---|---|---|
| n8n (workflow automation) | The job is a fixed flowchart: the same steps, in the same order, every time. | The job is open-ended work an agent does on its own computer (research, a report, a fix), with the configuration in git and a person approving what it changes. |
| OpenHands (coding agents) | You want a coding-agent control center for an engineering team. | Coding is one of many jobs: the same agents also work in Slack, on schedules and across 3,000+ apps, and every session is a sandbox on its own branch. |
| Paperclip (agent orchestration) | You already run agents such as Claude Code or Codex and want an org chart, budgets and a task board on top of them. | You want the platform to run the agents too: each session on its own cloud computer, from one repo that holds the agents, skills, memory and connectors. |
| Onyx, Open WebUI, LibreChat (chat and search) | You want a chat window or search over company documents. | You want agents that return finished work and take real actions in your tools, not only answers. |
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.
project (git repo + kortix.yaml)
└─ session ──> cloud computer: an isolated sandbox on a branch named after the session
└─ the OpenCode agent works
└─ change request ──> you review & merge ──> main
- Every session gets its own cloud computer — a disposable, isolated Linux sandbox on its own branch. The agent can install, run and break anything; only what it commits survives.
- Work reaches
mainonly through a change request you approve, so the company self-improves one reviewed change at a time. - Run thousands of sandboxes in parallel on the same config, each fully isolated, each feeding work back through change requests.
You can grep your entire company.
What people build with Kortix
An open-source Claude Cowork for your whole team
Kortix is the leading open-source alternative to Claude Cowork and ChatGPT Work. Your team uses it in the web app, in Slack and Microsoft Teams, or from the CLI. Agents run on real cloud computers and return finished work: decks, reports, code and replies. Any model provider with your own keys, or the ChatGPT plan you already pay for. Self-host for free, or use Kortix Cloud.
curl -fsSL https://kortix.com/install | bash kortix self-host start # your own box: one Docker Compose stack
AI agents in Slack and Microsoft Teams
Add the Kortix app to Slack, invite the bot to a channel, and mention it with a task. The message starts a session: the agent works on its own cloud computer with your connected tools and replies in the same thread. Microsoft Teams works the same way. Follow-ups stay in the same session.
Background coding agents in the cloud
Each session gets its own isolated sandbox and its own branch. The agent reproduces the bug, writes the fix, runs the tests and opens a change request. Every change request gets a preview you can open. Merge is default-deny for agents: you review the diff. Your local agent can start cloud sessions and go wide.
kortix sessions new --prompt "Reproduce issue #142, fix it, and open a change request" kortix cr ls # review what the agents propose
Replace Zapier-style automations with agents
A trigger starts a session on a cron schedule or a signed webhook, with nobody present. The agent reaches 3,000+ apps through one scoped token, plus MCP, OpenAPI, GraphQL and raw HTTP. Connector credentials are brokered server-side and never enter the machine.
# kortix.yaml triggers: - slug: daily-digest type: cron cron: '0 0 9 * * 1-5' prompt: Summarize yesterday's support tickets and open a change request with the digest.
An "AI employee" that asks before it acts
Give an agent a job, such as ticket triage, reply drafts or CRM updates. Set each tool to Allow, Ask or Block, down to the arguments of each call. An Ask holds the call until a person approves it, then the agent resumes. Approval gates are off until you set them.
# kortix.yaml agents: support-triage: file: agents/support-triage.md # what it does, in plain markdown connectors: all # what it may reach
Agents that survive a security review
One isolated sandbox per session. Per-resource permissions for people and agents. Roles, groups, and an audit trail. SAML 2.0 single sign-on and SCIM 2.0. Secrets are encrypted at rest with a key per project. Run it on Kortix Cloud, in your VPC, or on your own on-prem network. SOC 2 Type I is held; SOC 2 Type II is in progress.
An AI Operating System for your company
One repo is the company: agents, skills, memory, connectors and triggers are files, versioned and reviewed like code. Thousands of agents run in parallel on one config, each on its own cloud computer. An agent can edit its own configuration on its session branch and propose the change. A person approves it. What an AI Operating System is, part by part →
What you manage
| Agents | OpenCode agents with a scoped reach into tools — markdown at the baseline, with the whole OpenCode lifecycle open to you. One per role or task, installable in a click. An agent can edit its own configuration and propose the change; a person approves it. |
| Skills | Reusable know-how that encodes how your company does a job. Written once, shared into every session. |
| Memory | A living company brain — plain files today, a system that compounds what it learns over time. |
| Connectors | 3,000+ apps in a click — plus MCP, OpenAPI, GraphQL and raw HTTP. Credentials are brokered server-side through one scoped token and never enter the machine. |
| Secrets | Encrypted at rest, granted per agent, and injected into the sandbox at runtime. A granted secret is a real environment value inside that session. |
| Channels | Slack and Microsoft Teams are live; email is experimental, per project. Add the app, invite the bot to a channel, and @-mention it to start a session where your team already works. |
| Triggers | Cron and signed webhooks that spawn sessions automatically — every morning, or the instant something happens. |
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 schedule or trigger, end to end).
Why Kortix
- Open & yours. Open source and self-hostable — your data, your models, your infrastructure. No lock-in, fully auditable.
- A workforce, not one assistant. Org-scale specialist agents that run in parallel and compound a shared memory.
- Real work, not chat. Agents run on real cloud computers and return finished deliverables — and take real actions in your tools.
- Everything is code. Versioned, reviewable, portable, governable — never a black box.
- Bring your own models. Any provider, your own keys — or the ChatGPT subscription you already pay for.
Self-host
Kortix runs on your own infrastructure — a laptop, a VPS, your own VPC, or your own on-prem network. Start a production-style local instance from Docker images, then switch the CLI between Cloud and your own hosts:
kortix self-host start
kortix hosts use selfhost # ↔ kortix hosts use cloudThe first interactive setup asks only for the integration credentials that unlock managed git,
GitHub access, and Pipedream connectors — ports, local URLs, keys and Docker Compose defaults are
generated for you. Note that self-host start pulls its images from Docker Hub, so this is a
self-hosted install rather than a disconnected one.
Managed hosting is Kortix Cloud.
Enterprise & security
Built to survive a security review, not slip past one: one isolated machine per session · members, groups & roles that match your org · per-resource permissions for people and agents · connector credentials brokered server-side, so the raw key never reaches the sandbox · a secrets manager, encrypted at rest and injected at runtime · a full audit trail · merge that is deny-by-default for an agent · approval gates you switch on for the actions that matter · your own VPC or on-prem network.
Isolation is per provider: the Platinum provider runs microVMs, the default runs containers. Ask us and we'll tell you which one you're on.
Contributing
pnpm install pnpm dev # web + API (scripts/dev-local.sh) pnpm dev:web # web app only pnpm dev:api # API only pnpm dev:sandbox # build the local sandbox image pnpm build # build all packages pnpm nuke # tear down the local Docker environment
Apps live under apps/ (web, api, cli, desktop-electron, mobile, sandbox);
documentation source is in apps/web/content/docs. The whole platform ships under one version
(root VERSION) — API, frontend, CLI and desktop release together as vX.Y.Z.
Local secrets, test lanes, and the PR gate: CONTRIBUTING.md. Issues and pull requests are welcome.
We're building the thing that takes a company from human to AGI — and lets it keep every byte of itself on the way there.
来源:GitHub · github.com