You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
▶️ **[Watch the demo](https://github.com/user-attachments/assets/a74fa1cb-add0-463e-a23c-aa09b95d5135)** (~50s) — an OpenTag agent working a Slack thread: it renders a breakdown, a table, and a bar chart inline (**generative UI**) and files a ticket only after an **Approve** gate (**human-in-the-loop**).
18
18
19
-
> **Two ways to run it:****host it yourself** with the open-source SDK below — or skip the ops and **[sign up for the managed service →](https://go.copilotkit.ai/beyond-the-web-form)**(coming soon).
19
+
> **Two ways to run it:****host it yourself** with the open-source SDK below — or skip the ops and **[sign up for the managed service →](https://go.copilotkit.ai/opentag-managed-gh)** coming soon from CopilotKit.
20
20
21
21
## Quick start (self-hosted)
22
22
23
23
OpenTag ships inside the [CopilotKit monorepo](https://github.com/CopilotKit/CopilotKit) as a
24
-
first-class example (`examples/slack`) — that's the dependable way to run it today while the
24
+
first-class example (`examples/slack`). That's the dependable way to run it today while the
25
25
bot SDK packages finish publishing to npm. (A standalone `npm install` from this repo lights
26
26
up the moment they land — see [setup.md](./setup.md).)
27
27
28
-
You'll run two processes — the **agent** (the LLM backend) and the **bot** (the Slack
28
+
You'll run two processes: the **agent** (the LLM backend) and the **bot** (the Slack
29
29
connection) — and set three secrets.
30
30
31
31
**1. Create a Slack app.** At [api.slack.com/apps](https://api.slack.com/apps?new_app=1) →
@@ -54,7 +54,9 @@ pnpm --filter slack-example dev # the bot
54
54
> @OpenTag summarize this thread and file it as a bug
55
55
56
56
That's the whole loop. To wire up Linear, Notion, inline charts, Redis persistence, or to run
57
-
on Discord / Telegram / WhatsApp, see **[setup.md](./setup.md)**.
57
+
on Discord / Telegram / WhatsApp, see **[setup.md](./setup.md)**.
58
+
59
+
We won't lie to you, though. Setting up hosting for chat agents is not easy. To skip all of that heartache, go join the wait list for the CopilotKit managed service hosted on our Intelligence platform.
58
60
59
61
## Make it your own
60
62
@@ -74,12 +76,11 @@ The full architecture, the file-by-file map, and every integration live in
74
76
## Don't want to host it yourself?
75
77
76
78
Self-hosting means you run and scale the runtime, persistence, and inspection tooling yourself.
77
-
A **managed CopilotKit service** is coming soon — the same agent, without the ops: durable
79
+
A **managed CopilotKit service** is on its way. It's the same agent, without the ops: durable
78
80
threads, persistence, hosted inspection, and agents that improve from feedback (**Continuous
0 commit comments