kortix-ai /CompanyOS
Kortix CompanyOS – the open-source operating system for your company. Multiplayer AI agents, your company as code, sovereign on your infrastructure or ours.
★ 20,737⑂ 3,472👁 147⑃ 11,592● 1,153▤ 247
Download: v0.15.11 — Program agents, goals that stay with each chat, and a smoother connector sign-inv0.15.11 ↓0.15.112026-11-14
+22
Daily
+153
Weekly
20,737
stars
3,472
forks
147
watchers
11,592
prs
1,153
issues
247
releases
README
Kortix CompanyOS The open-source CompanyOS: the cloud-native agent harness for companies. Open Source · Extensible · Multiplayer · Sovereign Always-on agents that start on events, run in parallel and share one memory of your company. Build custom agents on pi and ship them from one git repo. Schedules, webhooks, your tools' events and your team's messages start them. My Kortix routes the work, and swarms of agents run it in parallel, each on its own cloud computer with state that persists. Agents connect to 3,000+ apps, build and host the apps your company needs, and land every change through a review your team approves. Share agents and context across your whole team. Open source, any model, on your infrastructure or ours. Website · Guide · Cloud · AI Transformation · Manifesto --- A new kind of system An agent today is one chat session on one machine. It waits for a person to type. It blocks while a long job runs. Every task it takes on shares one context. It stops when the laptop sleeps. A person can follow only a few such sessions at once, so human attention runs out long before the model does. Kortix CompanyOS takes the session out of the person's hands. It is a cloud-native agent harness: you write custom agents on pi, an open-source agent harness, and Kortix deploys them to the cloud and supplies everything around the agent loop that one session cannot. | | | | --- | --- | | Always on | Compute and state are separate. Every session runs on its own cloud computer. The computer sleeps 15 to 20 minutes after the last turn and wakes on the next message or event, with its full history. State lives in the repo, in Drive, in the session's /workspace and in the session's record. | | Event-driven | Triggers start agents from schedules, signed webhooks, connector events, App events and merged change requests. A filter in code drops noise before any model runs. A session subscribes to the events of its own work, and an agent sets its own check-in before it stops. | | One agent to talk to | You talk to My Kortix. It answers at once, hands writing, research, code and app work to the agent made for it in a session of its own, and tells you the result. Nothing it hands off blocks the conversation. A follow-up goes to the same agent, with everything that agent already knows. | | Swarms | A session hands work off in the background, runs a workflow that coordinates many agents, and messages other sessions. Every child reports back by itself. Thousands of agents run in parallel on one config. | | Long horizon | When a context fills, the agent continues in a fresh one and searches the session's full record for the exact lines it needs. Nothing is summarized. A job outlives one turn and one context window. | | Scales out | Compute is disposable and state persists, so capacity grows by adding computers, not by growing one. Each new session gets its own computer. A sleeping computer uses no compute. |
Top issues
#12655Browser journeys run in no CI job: the preview's browser lane crashes on load, the release shard is skipped4 comments · 2026-11-13#12122Self-host: on-box sandbox provider so agent sessions can run without a cloud sandbox0 comments · 2026-11-09#12065`kortix sessions new` refuses to start when a Claude subscription is the project's only model0 comments · 2026-11-08#11891security(self-host): the operator-address sign-up reservation fails open until the policy row exists0 comments · 2026-11-06#11890security(voice): a Meet guest can act as the trusted owner by taking their display name0 comments · 2026-11-06#11873Arcmira documentation MCP incorrectly described as requiring OAuth or an API key0 comments · 2026-11-05#11871security(kortixd): an agent can answer its own permission ask through its in-sandbox daemon0 comments · 2026-11-05#11715Feature request: Native local MCP bridge through the desktop app / agent-tunnel0 comments · 2026-11-04
Latest release
v0.15.11 — Program agents, goals that stay with each chat, and a smoother connector sign-in v0.15.11 2026-11-14New - Program agents: an agent can run your own code on every turn instead of a model, with a time limit and a payload input. - Chats in My Kortix keep their own goals and check-ins until the work is done. - A new workspace opens only after a model is connected, so the first chat always has a model to answer with. - One-prompt developer onboarding, and new factory templates. Improved - A finished connector sign-in lands on a Kortix page and tells the agent that it can continue. The sign-in card sits in the transcript under its step. - The CLI authorize page fills in the login code and asks y