Selling AI agents to your customers.
Embed agents in your SaaS or list them in a marketplace. ACP handles the per-tenant layer underneath so your team stays focused on the agent itself.
Open Source · MIT Licensed
The control plane
The control plane
for AI agents.
Xians ACP handles what surrounds your agents: multi-tenant access, conversations, webhooks, prompts, human tasks, scheduling, logs, and metrics. You build the agents. ACP runs the rest.
Self-hosted. Runtime-agnostic. MIT licensed.
Who uses it
Built for two kinds of teams.
Whether you ship agents to customers or run them internally, the control plane works the same way.
Running AI agents inside your organisation.
Deploy agents for your employees or internal customers. Self-hosted on your own infrastructure, with tenant isolation from day one.
Capabilities
What runs around your agents.
ACP wraps your agents with the operational layer they need. The agents themselves can use any framework, any model, any data layer.
-
Agent lifecycle
Register, version, deploy, and retire agents from one place.
-
Multi-tenancy
Tenant isolation with per-tenant configuration, secrets, and rollout state. One deployment, many customers or teams.
-
Interaction layer
One interface for conversations, webhooks, and human-in-the-loop tasks. Every channel reaches the agent the same way.
-
Prompts
Version, review, and roll out prompts. Promote between environments and roll back when behaviour drifts.
-
Observability
Structured logs, metrics, and traces for every tenant, agent, and conversation.
-
Business processes
Durable processes and schedulers. Long-running workflows survive restarts and retry safely.
Agent Studio
A full UI, included from day one.
Agent Studio is the built-in UI for Xians ACP. It is multi-tenant from the start. Here is what ACP manages for every tenant and every agent, out of the box.
Architecture
Xians ACP is the control plane in your agent stack.
Modern agent systems span four planes. Xians ACP owns the control plane. The other three are yours to shape.
Yours
Plane 1 · Interaction
How users and systems reach the agents
- Conversations & chat
- Human-in-the-loop tasks
- Webhooks & events
- Agent Studio (default UI)
- Your web / mobile UI
Surface agents anywhere your users already work. Ships with Agent Studio; bring your own UI on top.
Xians ACP
Plane 2 · Control
Where every agent and tenant is governed
- Lifecycle
- Multi-tenancy
- Interaction routing
- Prompt management
- Observability
- Business processes
MIT licensed. Self-hosted. One place for every agent and every tenant. This is the only plane ACP owns.
Yours
Plane 3 · Runtime
Where agents actually execute
- Any agent framework
- Any LLM / model provider
- MCP tools & servers
- Your cloud or on-prem
Pick the frameworks, models, and tooling that fit each problem. ACP does not decide for you.
Yours
Plane 4 · Data
What the agents read and write
- Integrations & SaaS APIs
- Internal services
- Databases & warehouses
- Vector stores & data platforms
Your data stays where it is. ACP orchestrates access. It does not own the data layer.
Out of the box
Production-ready from day one.
Drop ACP between your web server and your agents. You inherit horizontal scalability, zero-incoming-port security, durable fault tolerance, async orchestration, and full observability without wiring any of it yourself.
-
Auto horizontal scaling
Add or remove agent worker containers at any time. Temporal automatically distributes work. No orchestrator to rewrite, no service registry to maintain.
-
Zero incoming ports
Agents run in a private subnet with outbound-only pull connections. No inbound surface, no firewall holes, no accidental exposure.
-
Fault tolerance
Built-in retries, timeouts, and durable state. Workflows survive worker restarts, deploys, and infrastructure hiccups, right where they left off.
-
Decoupled by design
Agents focus on business logic. Routing, queues, conversation history, secrets, and observability live in the platform, not in your agent code.
-
Fully async by default
Even synchronous webhooks are queued and processed asynchronously. Stateless workers, configurable timeouts, massive throughput.
-
Multi-tenant isolation
Tenant-scoped state, secrets, prompts, and conversation history with centralised policy. One deployment, many customers or teams.
-
Durable long-running workflows
Orchestrate multi-step business processes that span minutes, hours, days, or years, with state managed reliably on Temporal.
-
Audit trail & tracing
Every workflow execution is logged with distributed tracing. Cost, performance, and behaviour are queryable per agent and per tenant.
Why ACP
Open. Neutral. Self-hosted.
-
MIT licensed
Read the code, fork it, ship it inside your product. No usage caps. No per-seat fees.
-
Neutral on the agent stack
Use any agent framework, any model, any data layer. ACP works around your choices.
-
Multi-tenant from the start
Durable workflows and observability are built in, not bolted on later.
Try it locally.
The docs walk through the architecture and how to run ACP on your machine in minutes.
Editions
Two ways to run Xians ACP.
The code is MIT-licensed for everyone. 99x adds a Commercial Support subscription for teams that need SLAs, security assurances, and a named engineering partner.
Community
MIT · Free forever
Self-host the full platform. No usage caps, no per-seat fees, no lock-in.
- Complete Xians ACP platform with all releases
- Agent Studio built-in UI
- All features including multi-tenancy, observability, HITL
- Community forum & GitHub issues
- Self-managed upgrades
Commercial Support
Backed by 99x
The same MIT code, with 99x engineering standing behind it under a support & assurance subscription.
- Priority roadmap input & feature requests
- Named-contact support with response-time SLAs
- Guaranteed critical hotfix & backport SLAs
- Continuous security scanning & CVE advisories
- Dependency upkeep & hardened LTS builds
- Contributor governance: reviewed commits, signed releases