Back to vendors
x

xpander.ai

Also known as: xpander, Xpander

Visit site
Entry priceTeam is usage based, billed in credits at one cent each, so $100 buys 10,000 credits. Enterprise is an annual contract from 50 agents, with no published price. There is no free tier.Full pricing detail

Governed runtime for enterprise AI agents: runs the agents teams already use, with approvals, audit, memory, knowledge and cloud, hybrid or air-gapped deployment.

xpander.ai is a governed runtime for enterprise AI agents. It runs the agents teams already use and governs every action they take. Agents are created with instructions, a harness and model, skills, approval rules and a runtime environment that acts as the agent's computer, or imported from existing definitions such as Claude Code agents. Skills come from a built-in catalog of API connectors, the customer's own OpenAPI specs and remote or local MCP servers, and workflows turn an agent into a graph of nodes with branching and human steps.

Work reaches agents through Xpander Chat, Slack and Microsoft Teams threads, email, WhatsApp, the API and MCP clients, or on recurring cron schedules. Agents carry organization-wide memories, per-user memories and thread history, and can search RAG knowledge bases. Risky actions wait for a named person's sign-off, each task records the agent's reasoning and call parameters, and an organization audit log keeps governed actions for up to 400 days.

Every model call passes through xpander's AI gateway, and sign-in runs through the customer's OIDC identity provider with credentials held in an external vault. xpander runs on its own cloud, as a Hybrid deployment with the runtime in the customer's cluster, or fully air-gapped. It is SOC 2 Type II certified, and ISO 27001, HIPAA and FedRAMP are in progress. A REST API, Python SDK and MCP endpoint expose agents to outside systems.

Vendor details

Canonical URL

https://xpander.ai

Category

Agent infrastructure

Subcategory

Agent runtime and backend

Funding status

Independent. Headquartered in Tel Aviv, Israel, with around 50 employees and roughly $3M raised. Founded around 2024.

Company status

independent

Use cases & customers

Primary use cases

agent backendagent runtimemulti agent orchestrationagent deploymentagent governance

Target customers

developersenterprise

Deployment options

SaaSVPCon-prem

Integrations

Agents hold skills from a built in catalog of API connectors, connectors generated from the customer's own OpenAPI specs for any private API, and remote or local MCP connectors. Agents can be invoked from the API, the Python SDK, MCP clients, webhooks, Slack and Microsoft Teams threads, email, WhatsApp, cron schedules or other agents.

In practice

Your team prototyped an agent in a framework but stalled for months building deployment, monitoring, and rollback. You bring it to xpander, which runs it with approval rules, a reasoning record on every task and an organization audit log, on xpander cloud or in your own cluster.

You run a long, multi step task that spans hours and must pause for a human approval midway. xpander holds the risky action for a named person's sign off, records the request and the decision on the task, and session storage keeps the thread's conversation history.

A regulated enterprise cannot send agent data to a vendor cloud. You self deploy xpander air gapped on your own Kubernetes with your own models, keeping execution and data inside your boundary.

Agentic Index coverage score

12.0 / 14 capabilities · 86%

Integrations & Tool Calling Full

Agents hold skills of four kinds, including API connectors from a built-in catalog, connectors generated from the customer's own OpenAPI spec, and remote or local MCP connectors, each governed with actions that can be held for approval.

Sourcexpander, docs.xpander.ai/connectors and connectors/add-a-skillread 2026-09-21

Workflow Orchestration Full

A workflow is an agent whose behavior is a graph of nodes instead of a single loop, with node types, branching and human steps. Agents can also call other agents as skills.

Sourcexpander, docs.xpander.ai/use/agents/workflowsread 2026-09-21

Knowledge Grounding & RAG Full

Agents attach RAG knowledge bases over the customer's own documents. Documents are added, listed and removed programmatically through the REST API and Python SDK, and the knowledge bases are queried by semantic search.

Sourcexpander, docs.xpander.ai/developers/knowledge/document-management and developers/knowledge/semantic-searchread 2026-09-21

Human Oversight & Guardrails Full

Risky actions wait for a named person's sign-off. Approval rules and gated commands are set per agent, permission modes apply on each run, connector actions can be held for approval, and approval requests and decisions are recorded on the task.

Sourcexpander, docs.xpander.ai/use/approvals and use/agents/permissionsread 2026-09-21

Security, Identity & Governance Full

xpander is SOC 2 Type II certified, with the report available under NDA. Users sign in through the customer's OIDC identity provider, such as Okta, Entra ID or Keycloak, scoped permissions control who may use, edit and share each agent, and credentials can be kept in an external vault.

Sourcexpander, docs.xpander.ai/resources/security-compliance/certifications-compliance and run/integrations/identity-providersread 2026-09-21

Observability & Auditability Full

Each task records the agent's reasoning entries and the parameters it chose for every call, so a failure can be traced to the model, the skill or the prompt. A separate organization audit log records governed actions such as agent changes, skill connections, credential use and sign-ins, with filters, download and retention of 90 or 400 days depending on event type.

Sourcexpander, docs.xpander.ai/use/agents/auditread 2026-09-21

Memory & State Persistence Full

Memory comes in three scopes. Agent memories are facts the agent always carries across the organization, user memories hold per-user facts that persist across sessions, and session storage keeps conversation history within a thread in Postgres.

Sourcexpander, docs.xpander.ai/developers/memory pagesread 2026-09-21

Deployment & Data Residency Full

xpander runs on xpander cloud, as a Hybrid deployment with the runtime in the customer's own cluster and the control plane on xpander cloud, or fully air-gapped with every component in the customer's environment. An EKS setup guide is available, and each agent can be placed in a cloud or self-hosted location.

Sourcexpander, docs.xpander.ai/self-hosted and run/locationsread 2026-09-21

Prebuilt Agents, Templates & Packs Partial

xpander ships one built-in agent, Omni, plus a skills registry of skill bundles and a way to import existing agent definitions such as Claude Code agents. Beyond Omni, customers assemble their own agents from these assets, as there is no set of separate ready-made agents.

Sourcexpander, docs.xpander.ai/use/skills-registry and use/agents/importread 2026-09-21

Triggers & Channel Coverage Full

Recurring cron schedules start agents automatically, and agents can book their own one-off re-checks. Work also reaches agents through Slack and Microsoft Teams threads, email, WhatsApp, the API and MCP clients.

Sourcexpander, docs.xpander.ai/use/agents/schedules and use/agents/channelsread 2026-09-21

Model Flexibility & Routing Full

Each agent's model is chosen in its configuration from the supported model providers, with the customer's own keys on cloud, hybrid and air-gapped installs. Every model call passes through xpander's AI gateway, which enforces the organization's model policy.

Sourcexpander, docs.xpander.ai/run/integrations/ai-vendors and run/integrations/ai-gatewayread 2026-09-21

APIs, SDKs & MCP Extensibility Full

A REST API creates and configures agents, starts runs and reads their record, and manages skills, knowledge and workflows. There is also a Python SDK, and an MCP endpoint with OAuth 2.1 lets outside clients reach xpander agents.

Sourcexpander, docs.xpander.ai/api-reference/rest-api, api-reference/sdk and api-reference/mcpread 2026-09-21

Testing, Debugging & Optimization Partial

Quality work centers on debugging. Each task records reasoning entries and call parameters so a failure can be traced to the model, the skill or the prompt, and Omni can review instructions. There is no evaluation harness, scored test cases or quality gate.

Sourcexpander, docs.xpander.ai/use/agents/auditread 2026-09-21

Browser & Computer Use Not documented

The agent's runtime environment is a computer with CLIs, packages, config files and scripts for running code, and the agent runs its code there. xpander names no browser or desktop interface that the agent operates itself. Browsing comes only through the Anchor Browser and Browserbase connectors, which are third-party products bought separately.

Sourcexpander, docs.xpander.ai/use/agents/runtime-environments and connectors/browserbaseread 2026-09-21

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 capabilityPartially Verified

An xpander agent can now build new tools for itself: a SKILL.md skill, a connector generated from an OpenAPI spec with its OAuth2 sign in, or a desktop connector that records the steps of an app with no API. Everything an agent builds starts as a draft. Admins test and approve these drafts in the skills registry and decide who may build them.

Bears on: Human approval / guardrails

View source
·Workflow orchestrationPartially Verified

Workflows are now generally available in xpander's new chat interface, with no preview entitlement needed. Users can also create and edit an agent's schedules from inside any conversation, and xpander now manages scheduling for agents running on Claude Code, Codex and OpenCode.

Bears on: Agent capability

View source
·Human approval / guardrailsPartially Verified

xpander.ai added a Secrets section that declares an agent's required credentials, validates personal connections, and resolves secrets on every turn. Its September 20 release also adds skill visibility scopes, grants for individual agents, and a public skill publishing API. Gated mode now holds web fetch and search calls for approval, with gated command editing available for Claude Code, Codex, and OpenCode agents.

Bears on: Security / enterprise

View source
View all 5 xpander.ai updates →Tracked since Aug 2026 · Verified from public vendor sources

Pricing

Team is usage based, billed in credits at one cent each, so $100 buys 10,000 credits. Enterprise is an annual contract from 50 agents, with no published price. There is no free tier.

Usage based, in credits worth one cent each. Agents spend 1 credit per wake and 1 credit per tool call, and model tokens bill at each model's published rate. Seats are free, so the bill follows the work agents do, not the number of users.

Free tier

Included quota

No usage is included free. Team credits cost one cent each ($100 is 10,000 credits), and seats are free. Enterprise is an annual license from 50 agents and adds full self hosting, SSO, an SLA, onboarding, A/B testing, external logging and vector DB access.

What is public

The Team credit price and what spends credits are public. A credit is worth one cent, agents spend 1 credit per wake and 1 per tool call, and model tokens bill at each model's published rate. Enterprise pricing is not public beyond an annual contract from 50 agents.

Billing mechanics

Team bills usage in credits worth one cent each, spent per agent wake, per tool call and on model tokens. Enterprise is a sales contracted annual license from 50 agents, with full self hosting. There is no self serve trial, and a pilot is set up after a demo.

Cost watchouts

Model tokens bill on top of the credits for wakes and tool calls, at each model's published rate, so without bring your own license, token spend at scale can dominate the bill. Always on embedded agents consume dedicated compute continuously.

Variable cost rationale

Team bills credits for the work agents do, 1 credit per agent wake and 1 per tool call, plus model tokens at each model's published rate. Agents that wake often, call tools heavily or process long contexts raise the bill, while seats add nothing. A spend cap throttles or pauses agents to prevent overages. Bring your own license can reduce token spend.

Additional watchouts

Cost comes from agent wakes, tool calls and model tokens at once, so a busy agent fleet spends credits on all three. Always on embedded agents carry dedicated compute cost, and model usage at scale benefits from bring your own license.

Overage / add-ons

Team usage draws down credits at one cent each, and no separate overage rate is published. A spend cap can be set to throttle or pause agents and prevent overages.

Sales call required

No, self serve available

Free / trial

No free tier or self serve trial, and a pilot is set up after a 30 minute demo

Lowest paid plan

Team, usage based, at one cent per credit ($100 is 10,000 credits)

Commercial notes

xpander.ai prices on the work agents do rather than on users ("Pricing is based on the work agents do, not on how many people use them."), with a credit based Team plan and an Enterprise license for teams that run agents on their own infrastructure. Billing runs through Stripe or AWS Marketplace. It is vendor neutral, with bring your own model and license.

Key ambiguities

Enterprise pricing is not public beyond an annual contract from 50 agents. Team is priced per credit, and no minimum purchase is stated.

Cancellation / refund

Enterprise is an annual contract from 50 agents. No cancellation or refund terms are published.

Support SLA / resale

Enterprise includes white glove onboarding and Tier 1 support. Available through AWS Marketplace.

Missing data

Enterprise dollar pricing, and any minimum purchase on Team, are not public.

Agentic Index verified 2026-06-30

Alternatives to xpander.ai

The closest documented capability profiles to xpander.ai 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.

  • Kestra12.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
  • Sourcegraph11.5 / 14A lighter documented profile than xpander.ai
  • Agno13.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and Testing, Debugging & Optimization
  • Thread AI11.0 / 14A lighter documented profile than xpander.ai
  • Tray.ai13.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs and Testing, Debugging & Optimization
  • Cartesia10.5 / 14A lighter documented profile than xpander.ai

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.