Back to vendors
N

Netlify

Also known as: Netlify Agent Runners

Visit site
Entry pricePersonal from $9 a month with 1,000 credits, and Pro at $20 a month with unlimited members. A free plan is available.Full pricing detail

Web platform whose Agent Runners run Claude Code, Codex, Gemini and OpenCode on live projects with previews and approval before publishing, plus an AI Gateway, durable workflows and an MCP server for agents.

Netlify is a composable web platform for building, deploying and running web projects, and increasingly for the agents that build them. Its agent layer is made up of Agent Runners, the AI Gateway, the Netlify MCP server, and the compute that AI features built on Netlify run on.

Agent Runners run coding agents (Claude Code, OpenAI Codex, Google Gemini, or OpenCode with open models such as Kimi, DeepSeek and GLM) directly from the Netlify dashboard or a phone. The agent starts with the project's code, environment variables, build settings and deploy pipeline, works in an isolated environment that never touches secrets, and produces a Deploy Preview and a list of changed files.

Nothing ships until someone with publishing permission merges the pull request or presses Publish, and every change rolls back in one click. When a prompt leaves a decision open, the agent pauses and waits for an answer. Ask mode answers questions about a project without changing it. Team roles decide who can run agents and who can publish.

For AI features the customer builds, the AI Gateway gives Netlify Functions access to OpenAI, Anthropic, Google and open models through their official SDKs with no API keys to manage, and Async Workloads add durable, event-triggered, multi-step workflows with retries and scheduling. Functions can be deployed to a chosen AWS region. The MCP server, API, CLI and Netlify Skills let outside coding agents create projects, deploy and manage settings.

Annual independent audits cover SOC 2 Type 2, ISO 27001, ISO 27018, PCI DSS and HIPAA, and SSO, SCIM and log drains come on Enterprise. Plans are credit based, with a Free plan, Personal at $9 a month with 1,000 credits, Pro at $20 a month with unlimited members and 3,000 credits, and a custom Enterprise plan. Agent runs and inference draw on the same credits.

Vendor details

Canonical URL

https://www.netlify.com

Category

Agent infrastructure

Subcategory

AI native web platform for building and deploying with agents

Funding status

Independent.

Company status

independent

Use cases & customers

Primary use cases

prompt to production app buildingAI code changes and bug fixesagent deployment and hostingAI gateway and web infrastructure

Target customers

web development teamsenterprises adopting AI developmentcross functional builders including PMs, designers, and marketers

Deployment options

cloudmanagedglobal edge

Integrations

Agent Runners run Claude Code, OpenAI Codex, Google Gemini and OpenCode (open models through OpenRouter) on Netlify projects, with GitHub pull requests and deploy notifications to Slack, webhooks or email. The AI Gateway serves OpenAI, Anthropic, Google and open models through their official SDKs with no provider keys. An MCP server, the Netlify API and CLI, and Netlify Skills bring the platform to outside coding agents.

In practice

Your backlog is full of small fixes that never justify pulling a developer off feature work. With Netlify Agent Runners you describe the change, an agent that knows your project implements it, and you approve a Deploy Preview before anything ships.

You want marketers and designers to update the site without handing them production. Internal Builders run agents and propose changes, while Developers keep the right to publish.

Your AI feature needs to run a multi-step job every night and survive flaky APIs. You write it as an Async Workload on Netlify, with each step retried on its own and models called through the AI Gateway with no keys to manage.

Agentic Index coverage score

10.5 / 14 capabilities · 75%

Integrations & Tool Calling Partial

An agent run acts inside the customer's Netlify project and its GitHub repository. It edits files, builds a Deploy Preview and can open or update a pull request, with deploy events sent to Slack, webhooks or email. Agent Runners have no catalog of connectors or custom tools the agent can call into other systems. The customer's own function code can call anything, but that is an integration the customer writes. Separately, the Netlify MCP server lets outside agents act on Netlify, and the AI Gateway connects the customer's code to models.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/make-changes-with-agent-runnersread 2026-09-22

Workflow Orchestration Full

Async Workloads, part of Netlify's AI runtime, give the customer's code a durable workflow runtime. A workload is broken into discrete steps with step.run, failed steps retry with default or custom limits without repeating steps that succeeded, steps can sleep or be scheduled, and workloads start on events.

A step can call a model through the AI Gateway between deterministic steps, so deterministic work and agent steps mix in one workload, with retries built into the runtime. Branching is written in code rather than drawn in a visual flow, and the task sequence inside Agent Runners belongs to Netlify, not the customer.

Sourcedocs.netlify.com/build/async-workloads/multi-step-workloadsread 2026-09-22

Knowledge Grounding & RAG Partial

Agent Runners ground each run in the customer's own project. The agent starts with the code, environment variables, build settings, deployment pipeline and Netlify primitives, and a team can add project context, such as prompt guidelines or a link to public documentation, that applies to every run. That is company data the agent works from. Netlify maintains no retrieval structure over the customer's content, such as an index or a search a query returns, so the agent reads the project it is working in. Netlify Skills are reference material about Netlify itself, not the customer's corpus.

Sourcenetlify.com/platform/agent-runnersread 2026-09-22

Human Oversight & Guardrails Full

Nothing an agent run does reaches production until a person ships it. Every Build mode run produces a Deploy Preview and a list of changed files for review, and shipping means merging the pull request or pressing Publish, which requires publishing permission. Internal Builders can propose changes while Developers control deployment, and any change rolls back in one click. When a prompt leaves open a decision that would change the result, the agent pauses, shows Waiting for answers, and holds its run until a person answers or skips, without spending credits. A run can be stopped at any point.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/make-changes-with-agent-runnersread 2026-09-22

Security, Identity & Governance Full

Annual independent audits cover AICPA SOC 2 Type 2, ISO 27001, ISO 27018, PCI DSS v4.0 and HIPAA, with the SOC 2 Type 2 report available to Enterprise customers in Netlify's Trust Center. Customers get their own controls alongside these audits. Team roles (Owner, Developer, Publisher, Internal Builder, Git Contributor, Reviewer) decide who may run agents and who may publish, SSO and SCIM come on Enterprise, and there is a team audit log. Agent runs happen in isolated environments that never touch secrets, with secret scanning on deploys.

Sourcenetlify.com/securityread 2026-09-22

Observability & Auditability Full

Every agent run leaves a log in the Agent Runs tab with its status and credit usage per task, the files it changed and its Deploy Preview, and every change is tracked, reversible and auditable, with who prompted what and when. A team audit log, separate from runtime logs, records team and project changes with retention set by plan. Function logs cover the customer's own agent code, and Enterprise log drains export logs to outside tools. Netlify does not say how much step detail a run log holds.

Sourcedocs.netlify.com/manage/accounts-and-billing/team-management/team-audit-logread 2026-09-22

Memory & State Persistence Partial

Within a run, work carries forward. An agent run is a series of tasks, each follow up prompt continues the same run with its earlier work in place, and a new project that cannot be finished in one run ends with a reviewable portion and a plan for the remainder. Project context that a team adds applies to every later run and is read by the agent as context. The agent writes and keeps no memory across runs, and there is no scope, lifetime or control to review, edit or delete memories. Async Workloads keep step results, and the platform uses them for retries.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/make-changes-with-agent-runnersread 2026-09-22

Deployment & Data Residency Full

Customers can choose where the AI runtime's compute runs, though Netlify itself is a managed cloud platform with no self hosted option. The functions that run AI Gateway calls and Async Workloads deploy to US East (Ohio) by default, a menu in project settings moves them to one of several AWS regions, and EU regions in Paris and Milan are available through support, with compliance named as a reason to choose. Netlify does not say where Agent Runners sandboxes and AI Gateway traffic run.

Sourcedocs.netlify.com/build/functions/optional-configurationread 2026-09-22

Prebuilt Agents, Templates & Packs Partial

Starter prompts for new projects come with Agent Runners, Netlify's packaged way to run coding agents on a live project, along with a prompt examples page for common jobs such as fixing broken links, redirects, content updates and new pages. Netlify Skills and context files teach outside coding agents the platform. These are working assets for one job, changing a web project. Netlify names no browsable catalog of production ready agents, templates or role specific agents.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/overviewread 2026-09-22

Triggers & Channel Coverage Full

Events and schedules wake the customer's agent code without a person. Async Workloads, which Netlify offers for AI work beside the AI Gateway and MCP server, start on events and can schedule or sleep between steps, and Scheduled Functions run AI Gateway code on a cron schedule. Agent Runners themselves are started by a person from the dashboard or a phone, with deploy notifications to Slack, webhooks or email.

Sourcedocs.netlify.com/build/async-workloads/overviewread 2026-09-22

Model Flexibility & Routing Full

Users pick both the agent and the model. Agent Runners run Claude Code, OpenAI Codex, Google Gemini or OpenCode, and each user can set the model and reasoning effort every agent uses, with OpenCode offering open models such as Kimi, DeepSeek and GLM through OpenRouter, routed only to providers with a zero data retention policy. The AI Gateway gives the customer's own code OpenAI, Anthropic, Google and open models through their official SDKs with no provider keys, and switching provider needs no rewrite. The model setting is a personal preference per user, not a team policy.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/overviewread 2026-09-22

APIs, SDKs & MCP Extensibility Full

From outside, an API with OAuth2 and a CLI drive the platform, and an MCP server, offered as a hosted endpoint or an npm package, lets coding agents create projects, deploy sites and manage environment variables. Netlify also publishes Netlify Skills and AI context files for coding agents, and an entry point at netlify.ai for agents that deploy on their own.

Sourcedocs.netlify.com/llms.txtread 2026-09-22

Testing, Debugging & Optimization Partial

Validation comes from running the agent's work. Every Build mode run produces a Deploy Preview on infrastructure that matches production, with the changed files listed, and a failed build or deploy is surfaced before anything ships, which checks the work in a real environment. There is no way to test agent workflows against fixtures or datasets before production, score output quality over time, or compare agents or models. The same preview holds the change until a person publishes it.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/make-changes-with-agent-runnersread 2026-09-22

Browser & Computer Use Not documented

There is no browser or desktop control. Agent Runners run coding agents in isolated environments that edit a project's files and build it, and a person checks the result in a Deploy Preview, with no agent operating a browser or desktop, clicking or typing in an interface. The customer's own agents get no browser or computer use environment either, and a code sandbox that edits files does not operate web interfaces where APIs are absent.

Sourcedocs.netlify.com/build/build-with-ai/agent-runners/overviewread 2026-09-22

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

·Agent capabilityVerified

Agent Runners can now read the review comments on pull requests it opened. A follow up prompt such as "address the comments on the PR" pulls the review comments from the linked pull request into the agent's context, so it can act on reviewer feedback without the user copying it from GitHub.

Bears on: Agent capability

View source
·Workflow orchestrationVerified

Netlify Server entered Early Access on credit based and credit enabled Enterprise plans, running an app backend as a long lived Node.js server that holds WebSocket and Server Sent Events connections, keeps state in memory and scales to zero. Netlify Server is rolling out to Agent Runners gradually over the following days, and the docs ship ready made Agent Runners prompts for building a first server.

Bears on: Workflow orchestration

View source
·MCP / tool calling / APIVerified

Asking the Netlify MCP server for recent deploys now opens a visual card in ChatGPT and other clients that support MCP Apps. The card lists up to five deploys with status, branch, creation time and any error message, links to the live site or the deploy in Netlify, and refreshes on its own for up to 15 minutes while a deploy is still running.

Bears on: Observability / auditability

View source
View all 13 Netlify updates →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Personal from $9 a month with 1,000 credits, and Pro at $20 a month with unlimited members. A free plan is available.

A flat monthly plan with a credit allowance shared by deploys, compute, AI Gateway inference and agent runs.

Free tier

Included quota

Free has a 300 credit limit a month. Personal includes 1,000 credits a month, Pro 3,000 credits a month with unlimited members, and Enterprise unlimited credits.

What is public

Netlify publishes Free, Personal ($9) and Pro ($20, unlimited members) credit plans with their allowances. Enterprise is quoted.

Billing mechanics

A flat monthly plan, not per member on Pro, with a credit allowance that agent runs, AI Gateway inference and platform usage draw down. Agent runs show credit usage per task, and a run waiting for answers spends no credits.

Cost watchouts

Agent runs, AI Gateway inference and platform usage all draw on the same credit allowance, so heavy agent use can exhaust a plan's credits well before other limits.

Variable cost rationale

Credits are metered. Deploys, compute, AI Gateway inference and agent runs all draw on the plan's monthly allowance, and each agent run consumes inference credits, so the bill grows with how much AI development a team does. The plan price itself is flat, and Pro is not charged per member. The Free plan has hard monthly limits that cannot be exceeded, agent runs stop or finish a reviewable portion when credits run low, and a run waiting for answers spends no credits.

Additional watchouts

Agent runs and inference share the credit allowance with the rest of the platform, so a plan's credits cover less when agent run volume is high.

Overage / add-ons

Usage beyond the plan's allowance requires more credits. Agent runs stop, or finish a reviewable portion, when a team runs low on credits.

Sales call required

No, self serve available

Free / trial

Free plan at $0 forever, with a 300 credit limit a month, including Agent Runners, functions and AI models

Lowest paid plan

Personal at $9 per month, with 1,000 credits a month

Key ambiguities

Plan prices are public, but total cost depends on how many credits agent runs and inference consume, which varies by task and model. Enterprise is quoted.

Support SLA / resale

Email support on all paid plans. Enterprise adds 24/7 support with a 99.99% SLA.

Missing data

Credits consumed per agent run or per model call are not listed. Enterprise pricing is quoted.

Agentic Index verified 2026-10-25

Alternatives to Netlify

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

  • Thread AI11.0 / 14Fuller documented coverage on Integrations & Tool Calling
  • Sourcegraph11.5 / 14Fuller documented coverage on Integrations & Tool Calling and Knowledge Grounding & RAG
  • Albato10.0 / 14Fuller documented coverage on Integrations & Tool Calling
  • Inngest10.0 / 14Fuller documented coverage on Testing, Debugging & Optimization
  • LiveKit11.0 / 14Fuller documented coverage on Integrations & Tool Calling and Testing, Debugging & Optimization
  • Redwood Software11.0 / 14Fuller documented coverage on Integrations & Tool Calling and Prebuilt Agents, Templates & Packs

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

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.