What are the best alternatives to RunWhen?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to RunWhen among SRE and DevOps agents are Avesha, Kubiya, AlertD, Doctor Droid. Each is graded on the same public evidence, and no vendor pays for placement.

Does RunWhen support MCP and tool calling?

Full under the Agentic Index verification standard. RunWhen publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: RunWhen's own MCP server, still in beta (hosted at mcp.beta.runwhen.com/mcp or local over stdio, bearer token or OAuth), exposes workspace search, chat rules and Tool Builder tools that commit SLXs to run on a schedule, and there is an API. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can RunWhen be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. RunWhen publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: There are three options. RunWhen Hosted runs in Google Cloud Canada and United States regions. Hybrid runs scripts in the customer's clusters through the Local agent. Self Hosted puts the full stack in the customer's VPC and suits air gappe. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can you bring your own model or route between providers with RunWhen?

Full under the Agentic Index verification standard. RunWhen publishes public evidence of bring your own model and bring your own key (BYOK), and of routing tasks between models or providers rather than being locked to one. Evidence basis: The platform supports bring your own LLM endpoint, so the customer chooses the model the assistants use. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

RunWhen

Q: Who is RunWhen for?

SRE teams, platform engineering teams, on-call responders, DevOps teams

Visit site

SRE / DevOps agentindependentVerified 2026-09-29

Entry priceSelf hosted license from $25,000 a year for 5,000 tickets. A PoC is $30,000 one time, and outcome based contracts start at $150,000.Full pricing detail

AI SRE platform whose assistants investigate issues and run troubleshooting Skills from a public registry of about 900, in chat or in the background on events and schedules, hosted, hybrid or self hosted.

RunWhen is an AI SRE platform for troubleshooting complex cloud systems. Its AI assistants investigate issues, run tasks and recommend actions in the customer's environment, choosing Skills from a public registry of about 900 tools for infrastructure, open source software, logs and metrics; each assistant has a persona, a Read Only or Read and Write permission level and confidence thresholds for what it suggests and what it runs. Foreground agents answer in chat, including Slack and Teams, and background agents run on events and schedules.

Customers build Skills in a harness with AI code review and commit them as SLXs through the Tool Builder, reachable from RunWhen's MCP server (beta) and API. RunWhen runs hosted, hybrid with scripts in the customer's clusters, or fully self hosted and air gapped, with bring your own LLM endpoint; its SOC 2 Type II audit is planned for general availability. It is sold as an annual self hosted license by ticket volume, with a paid PoC and outcome based contracts.

Vendor details

Canonical URL

https://www.runwhen.com

Company status

independent

Use cases & customers

Primary use cases

automated troubleshootingalert triage and RCAcontinuous production insightssafe remediation skills

Target customers

SRE teamsplatform engineering teamson-call respondersDevOps teams

Deployment options

RunWhen Hostedhybrid (scripts in your clusters)self-hosted in your VPC, air-gapped

Integrations

Skills for Kubernetes, cloud, open source software, logs and metrics from a public registry of about 900; ticket systems, Slack and Teams; MCP server (beta) and API.

In practice

An alert fires at night. A background agent picks it up, runs troubleshooting Skills from the registry against the customer's logs and metrics, and posts its findings and a recommended action in Slack.

A bank wants AI troubleshooting but cannot send data outside its network. It runs RunWhen self hosted in its own VPC, air gapped, with its own LLM endpoint.

An SRE team wants a routine health check run every morning. They build the check as a Skill, commit it as an SLX through the Tool Builder, and it runs on a schedule.

Sources & related URLs

Research sources

https://www.runwhen.com https://github.com/agamm/awesome-ai-sre

Agentic Index coverage score

10.0 / 14 capabilities · 71%

Integrations & Tool Calling	Full
Assistants investigate issues, run tasks and recommend actions in the customer's environment through Skills drawn from 896 Skill tools in the public registry for infrastructure, OSS, logs and metrics. A Read and Write permission level is available, and the license covers all ticket system integrations plus Slack and Teams. Sourcedocs.runwhen.com/docs/use/engineering-assistantsread 2026-09-29
Workflow Orchestration	Full
Several assistants, each with its own persona, permission level and confidence thresholds, choose which Skills to suggest or run. Foreground agents answer chat, and background agents run on events and cron. Customers author and commit SLXs through the Tool Builder, and these run on a schedule or on demand. Sourcedocs.runwhen.com/docs/use/engineering-assistantsread 2026-09-29
Knowledge Grounding & RAG	Full
Agents reference a database of prior runs, and workspace intelligence lets them search issues and browse the SLXs generated for the customer's discovered resources. That is a persisted store of findings about the customer's estate that agents can query. Sourcedocs.runwhen.com/docs/use/mcp-serverread 2026-09-29
Human Oversight & Guardrails	Partial
Each assistant carries a Read Only or Read and Write permission level, access limited to chosen users, and a Run Confidence threshold that decides what it runs and what it only suggests. Changes follow a Git based workflow. These are constraints the customer sets. There is no approval step before a task runs, and RunWhen says it works with a human in the loop but names no mechanism. Sourcedocs.runwhen.com/docs/use/engineering-assistantsread 2026-09-29
Security, Identity & Governance	Partial
Access runs on role based access control, authentication and authorization, audit logging and per assistant permission levels. The SOC 2 Type II audit is still ahead. RunWhen will undergo it every year once the product reaches general availability, so no attestation is held yet. Sourcerunwhen.com/security-informationread 2026-09-29
Observability & Auditability	Partial
Run sessions can be reviewed and the platform has audit logging, but RunWhen does not say what a run session records of the Skills an assistant ran, their commands or outputs. Sourcedocs.runwhen.com/docs/use/mcp-serverread 2026-09-29
Memory & State Persistence	Not documented
There is no memory with a set scope or lifetime. The database of prior runs that agents reference stores run results, the application's own data, not a memory layer. Sourcedocs.runwhen.com/docs/use/engineering-assistantsread 2026-09-29
Deployment & Data Residency	Full
There are three options. RunWhen Hosted runs in Google Cloud Canada and United States regions. Hybrid runs scripts in the customer's clusters through the Local agent. Self Hosted puts the full stack in the customer's VPC and suits air gapped and very high compliance environments. Sourcerunwhen.com/security-and-deploymentread 2026-09-29
Prebuilt Agents, Templates & Packs	Full
A public Skills Registry holds 896 Skill tools for infrastructure, OSS, logs and metrics. Each is a ready made troubleshooting task an assistant can pick up, reviewed before agents use it, and runnable as a standalone CLI tool. Sourcerunwhen.comread 2026-09-29
Triggers & Channel Coverage	Full
Background Agents run in response to events and in cron jobs, committed SLXs run on a schedule or on demand, and the platform is licensed by the tickets it works, beside chat in Slack and Teams. Sourcerunwhen.comread 2026-09-29
Model Flexibility & Routing	Full
The platform supports bring your own LLM endpoint, so the customer chooses the model the assistants use. Sourcerunwhen.comread 2026-09-29
APIs, SDKs & MCP Extensibility	Full
RunWhen's own MCP server, still in beta (hosted at mcp.beta.runwhen.com/mcp or local over stdio, bearer token or OAuth), exposes workspace search, chat rules and Tool Builder tools that commit SLXs to run on a schedule, and there is an API reference. Sourcedocs.runwhen.com/docs/use/mcp-serverread 2026-09-29
Testing, Debugging & Optimization	Partial
Skills built in the Skill Building Harness go through multiple levels of AI code review before an agent can pick them up, and they are tested against the RunWhen contract and live infrastructure, which validates the tools. User feedback that shows where new tools should be prioritized is mentioned only in passing. There is no evaluation of the assistants' own investigations. Sourcerunwhen.comread 2026-09-29
Browser & Computer Use	Not documented
Assistants run CLI and API Skills in the customer's environment. There is no browser, desktop or computer control. Sourcedocs.runwhen.com/docs/use/engineering-assistantsread 2026-09-29

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

Product updates

September 28, 2026·MCP / tool calling / APIVerified

RunWhen published the first tagged releases of runwhen-capability, the open source Python SDK its agent skills are written against, along with rwtask, a task host that runs each skill as a warm executor and doubles as a local command line tool. Versions 0.1.0 and 0.2.0 both shipped on September 28, and 0.2.0 lets custom skill bundles travel inside a request.

Bears on: MCP / tool calling / API

View source

View all RunWhen updates →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

Self hosted license from $25,000 a year for 5,000 tickets. A PoC is $30,000 one time, and outcome based contracts start at $150,000.

An annual self hosted license priced by ticket and chat volume, a one time PoC, and outcome based contracts for unlimited sessions.

What is public

RunWhen publishes the PoC price, each ticket band's annual license price and the floor for outcome based contracts.

Variable cost rationale

Tickets are the meter. The self hosted license is sold in annual bands of 5,000, 10,000 and 30,000 tickets, with chats added from the 10,000 band, so growing ticket volume moves the customer up a band. The band fixes the bill for the year, and no overage rate is published beyond the move to the next band. Unlimited sessions move to custom outcome based contracts from $150,000.

Overage / add-ons

Not published beyond moving to the next ticket band

Sales call required

Yes, required for paid access

Free / trial

None published. Open source Skills are published in a public registry

Lowest paid plan

5,000 Tickets at $25,000 a year, a self hosted platform license

Support SLA / resale

The PoC includes weekly check ins with the RunWhen engineering team and support by email, Slack and video during US Eastern business hours.

Agentic Index verified 2026-09-29

Official pricing page

Related vendors

Alternatives to RunWhen

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

Avesha9.5 / 14Adds documented Memory & State Persistence
Kubiya11.5 / 14Adds documented Memory & State PersistenceRunWhen vs Kubiya →
AlertD8.0 / 14A lighter documented profile than RunWhen
Doctor Droid11.5 / 14Adds documented Memory & State Persistence
Fabrix.ai12.5 / 14Adds documented Memory & State Persistence
Itential11.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Security, Identity & Governance

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 RunWhen with other vendors →Compare all SRE and DevOps agents →See where RunWhen ranks →

Data confidence: high

Head to head

RunWhen vs KubiyaRunWhen vs NudgeBee