AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Aug 7, 2026·Updated Aug 8, 2026
Independently verified against live vendor data on Aug 8, 2026.

Shared AI teammates in Slack, Teams, Discord, HubSpot and Zendesk that answer from connected team knowledge and act across 2,500+ tools. Exposes its own MCP server. From $79/mo billed yearly (USD), 14-day free trial.

How we scored it

Autonomy

4/5

Integrations

5/5

Pricing clarity

4/5

Evidence

3/5

Setup

5/5

The facts

Runbear puts shared AI teammates inside the tools an operations team already lives in. Agents are deployed into Slack, Microsoft Teams, Discord, HubSpot and Zendesk, where they join conversations, read connected team knowledge, and take action through connected tools. Per-user authorization means a shared agent still runs each action with the permissions of the person who asked, and every prompt and reply lands in an audit log the vendor states is SIEM-exportable. The build surface is no-code, and the paid tiers meter seats as builders rather than as end users. Integration depth is the strongest part of the product. The vendor's integrations page advertises 2,500+ integrations while its llms.txt and its own submission to this index both say 2,000+ tools. Both figures are published today and we have not resolved which is current. Verified by name on the integrations page: Slack, Microsoft Teams, HubSpot, Zendesk, Discord, Notion, Jira, Linear, Google Drive, Salesforce, Stripe and GitHub. Runbear works in both MCP directions, which is unusual. It acts as a client, describing itself as the first Slack MCP client, so a team can reach any external MCP server from a Slack channel. It also exposes its own hosted MCP server, documented at its developer docs host, which lets Claude Code, Claude Desktop, Cursor, VS Code, Windsurf and Zed connect inward over OAuth to read and manage the agents in a Runbear organization. That server is in early access and the vendor says its tool set is still expanding, with some agent settings remaining dashboard-only. Pricing is published in USD and metered by credits at one credit per model call, with no per-seat charge. Team is $99 per month month-to-month or $79 per month billed yearly, and includes 20,000 credits per month, 5 builders, Slack, Discord and Microsoft Teams, and MCP actions. Business is $399 per month month-to-month or $319 per month billed yearly, and includes 100,000 credits per month, 10 builders, all channels plus HubSpot and Zendesk, CRM integrations and bring-your-own LLM key. Enterprise is quote-only. The yearly saving is advertised as 20 percent and the vendor rounds the resulting figures down. Billing is cancel-anytime with no annual lock-in. What the entry price does not buy: HubSpot and Zendesk deployment, CRM integrations and bring-your-own-key model selection all sit on Business at four times the Team rate, so a support or revenue team that needs its CRM in the loop starts at $319 per month rather than $79. The 20,000 credit allowance on Team is consumed per model call rather than per user, so cost scales with agent chattiness rather than headcount. Credit allowances are identical on both billing states, so the yearly toggle changes price only. Runbear is not the right fit for a team wanting an autonomous outbound or customer-facing agent. The vendor gates sensitive actions such as refunds, deletes and outbound sends behind explicit human approval, and positions the product around drafting and routing inside a workspace rather than unattended external action. It is also early: one G2 review and seven Product Hunt reviews are the entire independent record. Current state Q3 2026. Runbear, Inc. is based in San Francisco and launched on Product Hunt in November 2023, where it placed fifth Dev Tool of the Week. Named production customers with published case studies include Aloware, LaserAway, Peak Ace, Power Real Estate Group, Peek.us and Got Game.

Pricing

subscription · $79/mo annual

View pricing ↗

Segment

b2b

Setup

easy

Verified

Aug 8, 2026

Transparency

Mostly Public

Contract

Monthly or Annual

Data training

Not Trained

Autonomy

Human Optional

Capabilities

autonomousworkflow-builderno-codemcp-serverbyokcrm-syncticket-resolutionknowledge-baseschedulingreportingmicrosoft-teams

Pros & Limitations

Editorial assessment

Pros

  • Works in both MCP directions, acting as a client from Slack and exposing its own hosted MCP server for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf and Zed.
  • Credit-based pricing with no per-seat charge, so cost tracks usage rather than headcount, and both published tiers list their exact credit allowance.
  • Per-user authorization on shared agents plus a SIEM-exportable audit log, and the vendor states plainly that customer data is not used for model training.

Limitations

  • The MCP server is in early access with an expanding tool set, and the vendor states some agent settings remain dashboard-only.
  • The vendor publishes two different integration counts, 2,500+ on its integrations page and 2,000+ in its llms.txt and its own submission, and we could not establish which is current.
  • Independent evidence is thin at one G2 review and seven Product Hunt reviews, with no Capterra or Trustpilot presence, and the SOC 2 Type II report is gated behind a trust center access request.

Technical Details

Deployment
webapicloud
Model architectureMulti-model (third-party LLMs)
Autonomous rateRunbear publishes no task-completion or autonomous-resolution rate. The only quantified customer outcomes are Got Game's reported 68+ hours saved on onboarding inductions, 34+ hours saved on staff policy guidance and 15+ days saved on executive progress meetings. Sensitive actions such as refunds, deletes and outbound sends require explicit human approval.
Integrations
SlackMicrosoft TeamsHubSpotZendeskDiscordNotionJiraLinearGoogle DriveSalesforceStripeGitHub
Security
SOC 2 Type II

Similar agents

Rating

4.0/ 5

Editorial score

How we score this →

Recognition

MCP Server VerifiedListed 2026
Embed these on your site →

Industries

SaaSReal EstateMarketingAgenciesEducationB2B

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature Runbear.

Compare

Related Content

Manage this listing

Badges, review collection, and listing updates for verified vendors.

Vendor dashboard →

Free · Every Two Weeks

AI Agent Price & Rating Tracker

Price changes, new agent launches, acquisitions, and rating updates across the AI agent market. Verified against live vendor data, not vendor marketing.

No spam. Unsubscribe anytime. We never share your email.