Free to get started

Start in the cloud in minutes, self-host the open source stack, or bring Beacon to your organization.

Run it your way

Open Source

Self-hosted agent telemetry for your own stack

$0forever

Get started with:

  • 20+ agents, including Claude Code, Codex and Cursor
  • Prompts, commands, diffs and token usage
  • Export to Elastic, S3 or any OTel collector
  • Offline threat detection
  • Local dashboard for sessions and costs
  • No account needed, and nothing leaves your machine

Zero infrastructure to manage

Beacon Cloud

Know what every agent did, and get better at using them

$0forever

Everything in Open Source, plus:

  • Every agent and machine in one timeline
  • See where your token spend goes
  • 50 findings for risks, reusable skills and habits
  • Turn findings into skills and fix prompts in one click
  • Let your agents search your past sessions over MCP
  • Share any session with a link

Scale your workspaceMost popular

Beacon Cloud Pro

Unlimited findings, and agents that learn from your history

$20/month

Everything in Beacon Cloud, plus:

  • Unlimited findings
  • Full MCP access for your agents: sessions, findings and feedback
  • Memories your agents can save and recall over MCP
  • Skills your agents can pull straight from your sessions
  • Full evidence trail on every finding
  • Real-time alerts and priority support

For organizations

Enterprise

Govern AI agents across your organization

Custom

Everything in Pro, plus:

  • Block or require approval for risky actions
  • Findings across your whole org
  • Agents on endpoints, in CI and in the cloud
  • Fleet rollout through Jamf, Intune or Fleet
  • SSO, RBAC and audit logs
  • Your own bucket and region
  • Dedicated SLA and support channel

Compare plans

Open SourceCloudProEnterprise
Price$0$0$20/moCustom
HostingYou run itManagedManagedManaged or your bucket
Agents20+20+20+20+, on endpoints, CI and cloud
Prompts, commands, diffs and token usage
Export to Elastic, S3 or OTel
Offline threat detection
Every agent and machine in one timeline—
Findings (risks, skills, habits)Local rules only50 includedUnlimitedUnlimited, org-wide
One-click skills and fix prompts—
MCP access—Session searchSessions, findings and feedbackSessions, findings and feedback
Agent memories over MCP——
Skills pulled from your sessions——
Share sessions by link—
Evidence trail——
Alerts—Daily digestReal-time emailReal-time and custom
Block or require approval for risky actions———
Fleet rollout (Jamf, Intune, Fleet)———
SSO, RBAC, audit logs———
SupportCommunityCommunityPriorityDedicated SLA

What are findings?

Beacon Cloud reviews your agent sessions and surfaces three kinds of findings.

Security

Risky things your agents did

Beacon flags actions that could hurt you, such as a secret pasted into a prompt, a destructive command, an agent bypassing its permissions, or a call to an unknown MCP server. Each finding shows what happened, which session it was in, and how to fix it.

Skill

Workflows worth reusing

When you walk an agent through the same steps more than once, Beacon notices and drafts a reusable skill from it. Download the skill and every agent you use can do the job right the first time.

Behavior

Patterns in how you work with agents

Beacon spots habits that cost you time or money, such as retry loops, abandoned sessions, approvals you always grant, or expensive models used for simple tasks. Each finding comes with a suggestion for working faster or cheaper.