Changelog

New updates and improvements to Runbear.

๐Ÿง  Claude Fable 5.2, GPT-6.1 Terra, and Models That Keep Up

Claude Fable 5.2 is in the model picker, the GPT Terra Stable row now runs GPT-6.1 Terra, and OpenAI Responses and Gemini agents now keep up with new model releases on their own.

๐Ÿง  New models

Claude Fable 5.2. Anthropic's newest Fable model is now the Fable option in the model picker on Claude Agent SDK and Anthropic agents. It runs only on the agent's own Anthropic API key, so Anthropic bills the model usage to your account. Agents saved on Fable 5.1 keep running. Model settings.

Model Selection on a Claude Agent SDK agent that uses its own Anthropic key, with Claude Fable 5.2 above the Stable Claude rows (sample agent)

GPT-6.1 Terra. On Claude Agent SDK agents, the GPT Terra Stable row now runs GPT-6.1 Terra. Agents pinned to a specific version stay where you put them.

Try it: open an agent, go to Settings, and look at Model Selection. To pick Fable 5.2, select a Claude model, then turn on Use my own Anthropic API key under API Key.

๐Ÿ”„ OpenAI Responses and Gemini agents stay current

Automatic latest. OpenAI Responses and Google Gemini agents now follow new releases in their tier, as Claude agents already do. An unpinned agent on GPT-5.6 Sol now runs GPT-6.1 Sol, for example. When you choose a specific release in the dashboard, the agent stays on it, and models without a tier, such as GPT-5.5 and GPT-4o, run as chosen.

GPT-6 on OpenAI Responses. The Stable rows GPT Astra, Sol, Terra and Luna now run GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra and GPT-6 Luna. GPT-5.6 and older releases are under Other versions. How Stable rows work.

Model Selection on an OpenAI Responses agent: Stable rows for GPT Astra, Sol, Terra and Luna, with Other versions below (sample agent)

โšก Also shipped

Pasted images in Microsoft Teams. Images pasted into the body of a Teams message now reach the agent, not only files attached with the paperclip.

Wide images keep their edges. On Anthropic agents, a wide image such as a screenshot of a table is scaled down instead of cropped, so the columns at the edges stay visible to the model.

Reconnect Confluence in one click. When a Confluence knowledge source needs you to sign in again, a message with a Reconnect button opens the sign-in, and a suspended source shows a notice that links to it. Confluence guide.

Google Drive service accounts. The Service Account picker shows a loading state until account emails arrive, then lists them sorted by email. If the lookup fails, you can retry and still switch accounts. Google Drive guide.

Website crawls identify as RunbearBot. The website crawler now identifies itself as RunbearBot and skips common analytics scripts, so its visits stop showing up as people in most site analytics. Website guide.

๐Ÿ—“๏ธ Set an End Date for Slack Knowledge, Plus Steadier Syncs

You can now decide where a Slack knowledge source stops, and Google Drive and website sources sync more of what you picked.

๐Ÿ—“๏ธ Set an end date for Slack knowledge

End Date for Slack sources. Slack knowledge sources have a new End Date under Start Date. Messages sent after that day are not synced, and replies posted after it are left out too, even in threads that started earlier. With no end date, the channel keeps syncing up to the present, as before.

The Slack knowledge source sheet with Start Date and the new End Date (sample agent)

The knowledge follows your changes. Move the date earlier and messages past it are removed. Move it later or clear it and the messages in between are synced. A note under the field tells you when sync stopped or when it will stop.

Try it: open an agent, go to Knowledge, open your Slack source, and pick an End Date. Slack knowledge guide.

๐Ÿ“š Knowledge syncs that get through

Google Docs that hit rate limits. When Google rate-limits a Doc export, Runbear tries other export formats where it can. A file that is still rate-limited no longer holds up the rest of the sync, and it is retried on the next scheduled run. Google Drive guide.

Website pages with file-style URLs. Pages like .../guide.html are crawled at their real address, and pages that return an error such as 404 are no longer added to your knowledge. Website guide.

Many Slack sources in one workspace. Each source now gets its turn instead of waiting behind a large one.

โšก Also shipped

Faster Activity for long conversations. Opening a long conversation in Insights โ†’ Activity is quicker, because each turn's debug trace loads only when you expand it.

Members and Profile after your sign-in lapses. Settings โ†’ Members and Profile no longer send you back to the home page. You are asked to sign in again and land on the page you wanted.

Gemini 4 Argon. Now in the model list for Google Gemini agents (gemini-4-argon).

๐Ÿง  Claude 5.5 Models, GPT-6.1 Sol, and an Activity Feed for Your Agents

If your agents use a Stable Claude model, they moved to the newest Claude models over the past few weeks without you changing a setting. And you can now open a real conversation and see what the agent did.

๐Ÿง  New models, already running

Claude 5.5 is the new Stable. Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5 now back the Claude Stable rows in the model picker. Agents on a Stable Claude row are already on 5.5. Agents pinned to a specific version stay where you put them. How Stable and pinned versions work.

Model Selection in agent Settings for a Claude Agent SDK agent: Stable rows for Claude and GPT, plus Gemini models (sample agent)

GPT-6.1 Sol. On Claude Agent SDK agents, the GPT Sol Stable row now runs GPT-6.1 Sol.

Gemini 3.8 Flash. Claude Agent SDK agents offer Gemini 3.8 Flash in place of 3.7 Flash. Agents that were on 3.7 Flash were moved to 3.8 Flash for you.

Claude Fable 5.1. Now in the model picker for agents that run on your own Anthropic API key.

Try a model before you switch. In Improve & Try, pick a different model for a single turn. The agent's saved model, and every channel it serves, stays the same.

Check yours: open an agent, go to Settings, and look at Model Selection.

๐Ÿ” See your agents' conversations in Activity

Each agent has a new Insights โ†’ Activity tab: a feed of real conversations across your channels. Open one to see the trace behind the reply, step by step, including tool calls. Learn more.

โšก Also shipped

A faster editor. Instructions is now an outline with an inline editor and Cmd/Ctrl+S. Tools is a list. Open a tool to switch individual actions on or off. Instructions, Tools.

The Instructions tab as an outline: main instructions and sections on the left, the inline editor on the right (sample agent)

Easier to find your way around. The Integrations page groups what you have connected into Channels, Knowledge and Tools, with a catalog you can browse by category. Settings is grouped into Account, Organization, Security and Billing.

More Slack options on the Claude Agent SDK runtime. Reply without @mention, and Trigger by keyword for top-level posts. Runtimes.

Another Slack workspace. Add a second workspace from the Slack integrations page, with the shared @Runbear bot or your own custom bot.

Your own Slack welcome. Custom Slack bots can set the greeting and options in Slack's assistant panel, in any language.

Clearer knowledge sync. Google Drive and SharePoint files we can't index now show as skipped, with the reason, and .md, .json and code files inside a selected Drive or SharePoint folder now sync. Disconnecting a source erases its indexed content.

Take over a knowledge source. If you don't own a Notion, SharePoint or Google Drive source, connect your own account to take it over. What is already synced stays.

Spreadsheets you can find by name. CSV and Excel files synced from now on also match a search for their filename, not just their contents.

A disconnected tool no longer ends the reply. If a tool needs someone to sign in, the agent still delivers its answer.

Connectors. A native Algolia connector, an API key option for Linear, and full action lists for 13 more connectors so you can switch off individual actions. Agents deployed to Zendesk now see the files attached to a new ticket.

Smaller touches. Browser tabs are titled after the page you are on, and knowledge source sheets save when you click Done and discard on Cancel.

๐Ÿš€ Ship an Agent Straight From Your Terminal

You already wrote your agent's instructions โ€” they're in your repo. Now you can ship them instead of re-authoring them in the dashboard.

๐Ÿ–ฅ๏ธ Ship your project as a teammate

The Runbear MCP server (early access) lets Claude Code, Claude Desktop and Cursor manage your agents. The runbear:deploy skill packs a local project and deploys it.

Deploy your project
/plugin marketplace add runbear-io/skills /plugin install runbear@runbear-skills /runbear:deploy --new "Triage"

The agent runs your files. On its next activation it loads the same CLAUDE.md, skills and code you have locally. Slack is a second ask in the same session.

โšก Also shipped

Six managed MCPs. Airtable, ClickUp, Apollo.io, Todoist, Salesforce and Amplitude โ€” pick the tile and authorize, no server to stand up.

โŒ˜K in the dashboard. Jump straight to an agent, a page or an action.

Gemini 3.7 Flash. Alongside 3.6 Flash, 3.5 Flash and Flash Lite, and 3.1 Pro. The 2.x generation is retired.

More model control. The full OpenAI catalog, reasoning effort and verbosity, and stable or pinned Anthropic versions with thinking effort.

Always-on memory compaction. Long threads keep what matters without the context growing unbounded.

Setup lives in Agent Skills.

๐Ÿš€ Summer Update: Agents That Do the Work, Set Themselves Up From Chat, and Learn From Feedback

Hand a Runbear agent a real task and it now runs the whole thing to the finish, right in the thread, instead of stopping at the first reply. It can also set itself up straight from chat, and it gets sharper from the feedback you give it. Here's what's new.

๐Ÿค– Introducing the Advanced agent (Beta)

This release's headline is a brand-new agent type. Give an Advanced agent a real task and it works through every step to a finished result, right in the thread, instead of stopping at the first reply.

  • Does the whole task, start to finish. Hand it a real task and it runs every step to a finished result, then drops the file back into the thread, instead of stopping at the first reply.
  • Works in a real environment. It has its own file system, so it can pull in the tools it needs, run code, and produce actual files like a PDF report, not just text.
  • Reuses your skills, remembers your context. Teach it a procedure once and it repeats it the same way every time, and it holds on to details from earlier conversations so nobody has to re-explain.

Turn it on. The Advanced agent adds skills, a real file system, and adaptive learning. Creating one takes a few clicks.

  • Open Agents and click Add Agent.
  • Name it, then choose Advanced. Standard is the fast default; Advanced is the one with skills, a file system, and adaptive learning.
  • Click Create Agent. Your Advanced agent is ready.

๐Ÿ› ๏ธ Build your agent right from chat

Setting an agent up used to mean clicking through settings. Now you tell it what you want in plain language and it wires itself up.

  • Connect the tools it needs. Ask for something that needs an app the agent isn't hooked up to yet, and it finds the right one and connects it on the spot.
  • Schedule recurring work. Say โ€œevery Monday at 9am, post a summaryโ€ and the agent sets up the scheduled job itself.
  • Set up triggers. Tell it to act when something happens, like a new ticket or a form submission, and it wires up the trigger for you.
  • You stay in control. Agents only reach for tools your workspace allows, and any job or trigger they set up follows your existing permissions and can be reviewed or turned off at any time.

๐ŸŽ“ Give feedback, teach your agents

Your thumbs-up and thumbs-down stop vanishing into a void. Now they feed straight back into how your agent works.

  • Rate any reply. A quick ๐Ÿ‘ or ๐Ÿ‘Ž in Slack or Teams tells your agent what good looks like.
  • Suggestions you can actually use. Runbear reviews your feedback nightly and drafts specific edits to your agent's instructions. You see exactly what would change and apply it after a quick look.

These upgrades are rolling out over the coming weeks, so some may not be switched on in your workspace yet. Your agents pick them up automatically as the rollout reaches you.

That's the update. Most of it came straight from your feedback, so keep it coming.

๐Ÿš€ Big Spring Update: Scheduled Triggers, an AI Agent Builder, Jira & Confluence, and More

We've been shipping fast. Here's a roundup of what's new in Runbear since our last update.

New

  • Triggers & scheduled automations. Your agents can now act on their own. Set up scheduled jobs (with a Run Now button and an active/inactive toggle) and event triggers that fire on real-world events, with a guided setup wizard, LLM-based pre-filtering, and automatic reconnect prompts when an integration needs re-auth.
  • AI-assisted agent builder & editor. Build an agent just by chatting, and refine its Instructions and Contexts with an AI chat panel. We also auto-generate agent descriptions and redesigned the navigation and Overview so everything is easier to find.
  • Slack-first onboarding. Getting started is now a single Slack-first flow with a persistent "Get Started" checklist and a friendlier welcome that walks you to your first working agent.
  • More integrations. Official Atlassian Jira and Confluence support, plus Granola, HiBob, Tiro, Apify, Google Cloud, native Gmail and Calendar, and custom MCP servers for personal agents.
  • The latest models. Claude Opus 4.7 (BYOK) with adaptive thinking, Claude Sonnet 4.6, and Google Gemini via Vertex AI. (Claude 3.7 Sonnet has reached end of life.)

Improved

  • A smarter Inbox Agent. Sharper Slack and Gmail draft replies that match your voice and tone, missed-message reminders so nothing slips, and less-intrusive insight notifications.
  • Slack experience. Native streaming replies with a live status pill and plan card, interactive choice buttons, response feedback buttons, and proper tables in Slack, plus a long list of rendering and reliability fixes.
  • Knowledge base quality & control. Exclude individual URLs from website sync, add an entire Google Drive at once, multi-tab Google Docs support, better Notion parsing, per-agent retrieval tuning, and stronger grounding to reduce hallucinations.
  • Reliability. More resilient Microsoft Teams delivery, graceful handling of broken integrations, and automatic model fallback to keep responses flowing.

๐Ÿ“ฅ Inbox Agent (Beta): Open every client message with context, actions, and a reply ready

โœจ Whatโ€™s new

  • Live in under 5 minutes: Connect your inbox and start immediately. No complicated setup. No workflow cha
  • nges.
  • Activates the second an email arrives: As soon as a client email hits your inbox, Inbox Agent pre-populates automatically.
  • Context, already assembled: It pulls the relevant account story from the tools you already use, including CRM, calendar, docs, and past threads, and puts it where you need it.
  • What you need to know, summarized: Key updates, decisions, open questions, and risks are condensed into a short, scannable summary.
  • Next steps you can click: Suggested actions like update CRM, loop in a teammate, or create a task, all clickable directly from the inbox.
  • Replies done for you: A clear, confident reply draft appears instantly. Send as-is or make a quick edit.
  • [Coming soon] One system across tools: Works alongside Runbearโ€™s AI Teammates in Slack, so internal execution keeps pace with external conversations.

๐Ÿ”‘ Why it matters

  • Prep work disappears: No tab switching. No searching history. No guessing what changed.
  • Replies get dramatically faster: Teams testing Inbox Agent are replying up to 10ร— faster, largely because context and actions are already prepared.
  • You sound sharp by default: Every response reflects real account context, not memory or last-minute reconstruction.
  • Better timing, better outcomes: Upsell moments, renewal risk, and follow-ups surface while the thread is active, not after itโ€™s cold.

๐Ÿšฅ Beta signal

  • Already in use by early-access teams managing high-volume client inboxes.
  • Built for seat-based rollout and enterprise use from day one.

๐Ÿš€ Try it now

If your inbox drives deals, renewals, and customer relationships, Inbox Agent is built for you.

๐Ÿ‘‰ Try it now at app.runbear.io/inbox.

๐Ÿ—“๏ธ Have questions? Book a demo to see it working on real emails and talk through a team rollout.

Message Insights and Better Debugging Tools

๐Ÿฆƒ Happy Thanksgiving! Weโ€™re grateful for your support and excited to share a few new updates that just landed ๐Ÿš€

๐Ÿ†• Message Insights

Weโ€™ve added a new way to understand what users are actually asking your AI agents โ€” without digging through raw message logs.

๐Ÿ” Grouped User Questions

Instead of showing every message individually, we now automatically group similar user questions to highlight common themes. This helps you quickly spot patterns such as frequent requests, confusing areas, or recurring problems.

๐Ÿงฉ Improve Agents with Context

Inside each grouped topic, you can add additional context or instructions to help your AI agents respond more accurately. This makes it easier to iterate on agent quality and improve resolution rates.

๐Ÿ“ Where to Find It

Go to your Agent page โ†’ Messages tab (available in the new editor). Youโ€™ll find:

  • Common topics
  • Unresolved user questions
  • Clustered messages for easier review

๐Ÿ” Privacy Controls

This feature is only available if your organization admin has enabled Message Insights, ensuring user privacy is respected.

๐Ÿ› ๏ธ Better Trigger Debugging

You can now view status, messages, and execution logs for each Trigger โ€” and even replay past events to test them more easily. Debugging made simple!

Pricing Update

From Messages to Credits

We're moving from message-based to credit-based billing because not all AI interactions are equal. A simple knowledge base Q&A consumes far fewer resources than a complex workflow with multiple tool integrations (MCP) and document processing.

With credits, simple Q&A costs fewer credits while complex workflows cost more, reflecting actual computational cost. If you primarily use knowledge base queries, you'll handle significantly more interactions for the same price.

Introducing Pay-as-You-Go

Previously, hitting your plan's limit meant upgrading or stopping until the next cycle. Now with pay-as-you-go, set your own overage limits and automatically purchase additional credits when neededโ€”no service interruptions, no forced upgrades for temporary usage spikes.

Flexible Agent Limits

Previously, if you needed one more agent beyond your plan's limit, you had to upgrade your entire plan. Each plan still includes a base number of agents, but now you can create additional agents with pay-as-you-goโ€”paying only for what you use without upgrading your entire plan.

Why We Made These Changes

Your feedback was clear: message-based pricing didn't match how you wanted to use Runbear. Sophisticated workflows felt constrained by limits that didn't reflect their value, while simple Q&A users wanted more queries without constant limit concerns. Rigid plan tiers forced unnecessary upgrades for small increases in usage.

๐Ÿš€ Event Triggers, New Agent Creation With Context, and More

Event Trigger (Beta)

Runbear is now available everywhere! ๐ŸŽ‰ Weโ€™re excited to introduce Event Triggers, a powerful new way to run your AI agents automatically in response to events.

Think of it as giving your agents superpowersโ€”able to take action automatically:

  • Auto-reply to emails in real time.
  • Link new Zendesk tickets to the right Linear issues.
  • Send meeting summaries to participants right after Zoom calls.

This is just the beginning. Unlock your imagination and let AI handle the repetitive work, so your team can focus on what matters most.

โšก Beta availability: Weโ€™re rolling this out gradually during the beta period. Stay tuned as access expands!

New Agent Form (with Agent Context)

Now you can create agents by simply choosing your toolsโ€”no prompts or complicated setup required. Once created, you can continue to teach your agents with Agent Contexts. (Or you can teach them directly in Slack, e.g., โ€œ@Agent, remember that you can find revenue from here: https//docs.google.com/...โ€)

Prefer more control? No worries! You can always switch back to the classic editor for full customization.

Enjoy a smoother, faster way to bring your AI agents to life, without the hassle.

Other changes

  • Official MCP Integrations: weโ€™ve added official support for Notion and Hubspot MCP. This brings smoother usability and an overall better experience.
  • Integration Guidance: Runbear can now recommend which integrations youโ€™ll need when your request depends on tools that arenโ€™t yet connected, making it easier to get set up without guesswork.