How much does Keragon cost?

Starter $149/mo ($99 annual), Professional $399 ($269), Scale Up $1,499 ($995), Enterprise custom; runs and AI credits included with published overage; 14-day free trial.

What are the best alternatives to Keragon?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Keragon among healthcare agents are Luma Health, Sully.ai, Cohere Health, Notable. Each is graded on the same public evidence, and no vendor pays for placement.

Does Keragon support MCP and tool calling?

Full under the Agentic Index verification standard. Keragon publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Keragon MCP lets a customer's own AI client (ChatGPT, Claude, Gemini) act across 400+ connectors under the customer's BAA with least-privilege access, and workflows accept inbound webhooks and reach any API through a universal HTTP connecto. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Keragon have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Keragon publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: The platform is SOC 2 Type II audited with continuous control monitoring, and HIPAA compliant with a BAA on every paid plan and a trust center with the report and live control status. Google sign in, two factor authentication and view, buil. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Keragon give you tracing and observability into agent runs?

Full under the Agentic Index verification standard. Keragon publishes public evidence of tracing, observability and audit logging into agent runs, so a team can see what an agent did and why. Evidence basis: An immutable activity log records every workflow run, agent action and connection change, each agent and MCP tool call is logged and traceable to a user or agent step by step, PHI access is logged and replayable, and execution monitoring ra. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Keragon

Q: Who is Keragon for?

private practices, multi-location clinics, digital health companies

Also known as: Keragon Agents, Keragon AI

Visit site

Healthcare agentindependentVerified 2026-09-29

Entry price$149/mo (Starter), $99/mo billed annuallyFull pricing detail

HIPAA-compliant healthcare automation: no-code workflows built from plain English, AI agents with human-review checkpoints, and an MCP layer for ChatGPT, Claude and Gemini across 400+ healthcare integrations; SOC 2 Type II, published pricing from $149 a month.

Keragon is a HIPAA-compliant automation platform for healthcare organizations, from solo practices to enterprises. Workflows are described in plain English and built as multi-step, branching automations that start from webhooks or polling triggers; Agents are AI teammates (AI receptionist, answering service, scheduling and balance follow-up) that handle judgment calls and hand off to and from workflows; and Keragon MCP lets a customer's own AI client act across the same 400+ connectors under the customer's BAA.

Agents are bounded to the tools and actions granted, connectors are read-only until write access is given, and human-review checkpoints make an agent show its plan and wait for sign-off on sensitive actions. Keragon maintains evaluations and safety rules for every agent, and every workflow run, agent action and MCP tool call lands in an immutable HIPAA audit log. It is SOC 2 Type II audited with a trust center, includes a BAA on every paid plan, and offers SSO, 2FA and roles on every plan. Pricing is published: Starter $149 a month, Professional $399 and Scale Up $1,499, with annual discounts, Enterprise custom, and a 14-day free trial.

Vendor details

Canonical URL

https://www.keragon.com

Funding status

$10.5M total raised

Company status

independent

Use cases & customers

Primary use cases

healthcare workflow automationpatient intake automationappointment reminders and no-show recoveryEHR data syncconnecting external AI agents to healthcare tools via MCP

Target customers

private practicesmulti-location clinicsdigital health companies

Deployment options

SaaS

Integrations

400+ healthcare integrations (EHRs, CRMs, scheduling, communication and more) with connector- and action-level scoping, a universal HTTP connector, webhook and polling triggers, and Keragon MCP for ChatGPT, Claude and Gemini.

In practice

A clinic lets the No Show Recovery Specialist reach patients who missed a visit, find a new time on the calendar and rebook them.

A front desk team has the Insurance Verification Specialist check coverage, benefits and copays for every scheduled patient before they arrive.

A care team asks Claude, through Keragon MCP, to pull a patient's recent records from the EHR, with only the tools the practice whitelisted available.

Sources & related URLs

Research sources

https://www.keragon.com/ https://www.keragon.com/agents https://www.keragon.com/pricing https://www.prnewswire.com/news-releases/keragon-ai-turns-plain-english-into-hipaa-compliant-healthcare-automation-302686256.html

Agentic Index coverage score

9.5 / 14 capabilities · 68%

Integrations & Tool Calling	Full
There are 400+ healthcare integrations (EHRs, CRMs, scheduling, communication) plus a universal HTTP connector for any system with an API, with connector- and action-level scoping that keeps connections read-only until write access is granted. More than 30 EHRs are supported, among them athenahealth, Elation, Healthie, DrChrono, Tebra, eClinicalWorks and ModMed, along with forms and billing systems. SourceKeragon, keragon.com/agents and /mcp; keragon.com/pricingread 2026-10-05
Workflow Orchestration	Full
A no code builder creates multi step workflows with branching and conditional steps, and the customer configures them. A workflow can hand off to an agent for a judgment call, and an agent can trigger a workflow for deterministic steps. To build an agent, a customer sets a trigger, briefs it in plain English, gives it the tools it needs and tests it on real cases before it goes live. SourceKeragon, keragon.com/agentsread 2026-10-05
Knowledge Grounding & RAG	Not documented
Agents get no knowledge base or document store to search, and they act on data from connected tools within the scopes granted. The Pre Visit Prep Specialist, for example, reads intake responses, prior visit notes, active medications and recent labs from connected systems and turns them into a structured patient brief. SourceKeragon, keragon.com/agentsread 2026-10-05
Human Oversight & Guardrails	Full
Human review checkpoints require a person to review and approve before an agent takes a sensitive action. The agent shows its plan and waits for sign-off. Agents are bounded to granted tools and rules, and connectors are read only until write access is granted per action. Human checkpoints come on every plan, along with usage alerts and spend controls. SourceKeragon, keragon.com/agents, /security and /pricing; keragon.com/securityread 2026-10-05
Security, Identity & Governance	Full
The platform is SOC 2 Type II audited with continuous control monitoring, and HIPAA compliant with a BAA on every paid plan and a trust center with the report and live control status. Google sign in, two factor authentication and view, build and manage roles come on every plan, and SAML and LDAP single sign on come on Enterprise. Connectors are scoped by connector and action, and credentials sit in a central encrypted store that builders never see. Data is encrypted with AES-256 at rest and TLS 1.2 or later in transit. SourceKeragon, keragon.com/security and /pricingread 2026-10-05
Observability & Auditability	Full
An immutable activity log records every workflow run, agent action and connection change, each agent and MCP tool call is logged and traceable to a user or agent step by step, PHI access is logged and replayable, and execution monitoring raises alerts with automatic retries. Every access, edit and deletion of PHI shows who did what, and every read and write through Keragon MCP is logged for review. SourceKeragon, keragon.com/security and /mcpread 2026-10-05
Memory & State Persistence	Not documented
There is no stated memory that agents keep between runs. PHI is processed in transit and not stored unless the customer configures storage, and AI providers retain none of the data. Customer data is deleted at offboarding under Keragon's retention policy. SourceKeragon, keragon.com/securityread 2026-10-05
Deployment & Data Residency	Not documented
Keragon runs on AWS but names no hosting region, offers no choice of region and has no option to run in the customer's own environment or on premises. PHI passes through in transit and is not stored unless the customer sets that up. AWS and Google are its core subprocessors, and business continuity and disaster recovery plans are tested regularly. SourceKeragon, keragon.com/securityread 2026-10-05
Prebuilt Agents, Templates & Packs	Full
A templates gallery holds prebuilt healthcare workflows and named agents (AI receptionist, AI answering service, AI scheduling agent, balance follow-up), each doing its own job. The agents also include a Patient Intake Specialist, an Appointment Reminder Agent, a No Show Recovery Specialist, an Insurance Verification Specialist, a New Patient Acquisition Agent and a Pre Visit Prep Specialist. They do jobs such as rebooking missed visits, checking coverage and copays before a visit, and booking website leads onto a provider's calendar. SourceKeragon, keragon.com/agentsread 2026-10-05
Triggers & Channel Coverage	Full
Workflows start from inbound webhooks and from polling triggers that check connected systems as often as every minute, and the AI receptionist agent answers patient calls. Polling runs every 5 minutes on Starter and Professional and every minute on Scale Up and Enterprise. Agents start on a schedule or on an event the customer sets. SourceKeragon, keragon.com/pricing and /agentsread 2026-10-05
Model Flexibility & Routing	Partial
A bring your own LLM provider option for agent intelligence is listed for Enterprise, subject to availability on request. Otherwise the agents' model is not named. Keragon MCP lets a customer's own AI client, such as ChatGPT or Claude, use Keragon tools from outside, which does not change the model behind Keragon's own agents. Each agent action uses a few AI credits, and plans include from 5,000 to 60,000 credits a month. SourceKeragon, keragon.com/pricing and /mcpread 2026-10-05
APIs, SDKs & MCP Extensibility	Full
Keragon MCP lets a customer's own AI client (ChatGPT, Claude, Gemini) act across 400+ connectors under the customer's BAA with least-privilege access, and workflows accept inbound webhooks and reach any API through a universal HTTP connector. The MCP endpoint also works with Cursor and with voice AI agents. App credentials stay in Keragon and never reach the AI client, and only the tools a customer whitelists are exposed. SourceKeragon, keragon.com/mcpread 2026-10-05
Testing, Debugging & Optimization	Full
Keragon maintains evaluations and safety rules for every agent by default, agents take test runs before they go live, test runs of workflows are free, and failed workflows are diagnosed and fixed by the platform. A test run previews exactly what an agent will do before it touches a live system, and agents are tested on real cases. SourceKeragon, keragon.com/pricing and /agentsread 2026-10-05
Browser & Computer Use	Not documented
There is no stated browser, desktop or computer control. Agents and workflows act through connectors, webhooks and HTTP APIs. Agents reach patients by text, email and voice, and reach systems such as EHRs and schedulers through connectors. SourceKeragon, keragon.com/agents; keragon.com/pricingread 2026-10-05

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

$149/mo (Starter), $99/mo billed annually

Monthly plan with included workflow runs and AI agent credits, plus per-run overage.

Trial available

What is public

Full tier table on the pricing page: Starter $149 ($99 annual), Professional $399 ($269), Scale Up $1,499 ($995), Enterprise custom; runs, credits, published agent limits, per-run overage rates and caps, AI credit discounts, MCP call allowance and a machine-readable pricing file.

Cost watchouts

Failed runs count against run limits, overage runs are capped per tier, and agent actions draw a variable number of credits per task.

Variable cost rationale

Tiered subscription with included runs and credits; overage runs and extra credits are metered at published rates, and agent actions consume variable credits.

Overage / add-ons

Runs beyond the monthly allowance bill at $0.15 (Starter), $0.07 (Professional) or $0.02 (Scale Up) per run up to a monthly cap; extra AI credits at a per-credit rate discounted 33 or 50 percent on higher plans (Starter capped at 5,000); failed runs count.

Sales call required

No, self serve available

Free / trial

14-day free trial, no credit card; test runs free; MCP free in beta (100 tool calls a day).

Lowest paid plan

Starter, $149 a month or $99 a month billed annually ($1,188 a year): 200 workflow runs, 5,000 agent credits, 3 published agents or workflows.

Agentic Index verified 2026-09-29

Official pricing page

Related vendors

Alternatives to Keragon

The closest documented capability profiles to Keragon among healthcare agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Luma Health10.0 / 14Adds documented Knowledge Grounding & RAG and Memory & State Persistence
Sully.ai9.0 / 14Adds documented Knowledge Grounding & RAG
Cohere Health10.5 / 14Adds documented Knowledge Grounding & RAG and Deployment & Data Residency
Notable9.5 / 14Adds documented Knowledge Grounding & RAG and Browser & Computer Use
Ember Copilot9.0 / 14Adds documented Knowledge Grounding & RAG
Infinitus10.0 / 14Adds documented Knowledge Grounding & RAG and Browser & Computer Use

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Keragon with other vendors →Compare all healthcare agents →See where Keragon ranks →

Data confidence: high

Head to head

Keragon vs XCaliber Health