Xagent · Your busywork, handled by agents.

Your busywork, handled by agents.

Tell Xagent what you need. It plans the work, runs it, and hands back the result.

12,480tasks this month
$1,284monthly spend
$0.10avg cost per task
98.2%task success rate
au.cloud.xagent.co / taskLIVE
Agent development
Resources
All tasks
Ssummer

ai_news_podcast_weekly.mp3
0:00 / 4:11
Describe your task...
deepseek-v30 input · 0 output tokensSend
Execution PlanVerticalHorizontal
DAG Execution Graph · Execution Phase
Recreated from the Xagent app. Live product screenshot to follow.
DONESummarised this quarter's pipeline RUNNINGTriaging 14 support tickets DONEDrafted Monday's QBR deck RUNNINGQualifying 6 inbound leads DONEAnswered 32 policy questions SCHEDULEDWeekly usage report, Fridays 9am DONETurned a brief into 4 LinkedIn posts DONESummarised this quarter's pipeline RUNNINGTriaging 14 support tickets DONEDrafted Monday's QBR deck RUNNINGQualifying 6 inbound leads DONEAnswered 32 policy questions SCHEDULEDWeekly usage report, Fridays 9am DONETurned a brief into 4 LinkedIn posts
Trusted by teams building at scale
SiemensYum! BrandsTFCBerry GenomicsXW BankAIAEverbright SecuritiesSiemensYum! BrandsTFCBerry GenomicsXW BankAIAEverbright Securities

Four reasons teams pick Xagent.

The points that matter in an enterprise evaluation, up front.

Built for enterprise

Security and visibility your compliance team will ask for. Included, not added later.

  • Admin & team workspaces
  • SSO (Google OIDC)
  • Run logs & traces
  • Token usage & monitoring

Simple to use

A plain-language request is the whole spec. No diagrams to draw, no glue code to write.

  • Describe tasks in your own words
  • Save repeat work as agents
  • Start from ready-made templates

Model-agnostic

Open models or API providers. Never locked to one vendor's model or cloud.

  • Qwen, DeepSeek, OpenAI & more
  • Any OpenAI-compatible endpoint
  • Choose the model per step
With Xinference

End-to-end stack

The only agent platform with its own inference layer. One team, one stack, GPU to agent.

  • Self-hosted models via Xinference
  • Data never leaves your environment
  • Up to 70% lower inference cost

Five specialists. One planner.

Every workspace ships with a team that plans together, checks its own work, and gets things back to you finished.

Support agent, a felted chameleon figurine
SUPPORT
Tickets · chat · docs Q&A
answering 3 tickets
Employee file312tickets resolved this month
zendeskmail.draftkb.search
Escalates to a human when unsure
Growth agent, a felted lion figurine
GROWTH
Leads · outreach · posts
drafting 2 campaigns
Employee file48leads qualified this month
linkedin.postweb.searchcrm.update
Every send logged, every claim sourced
TEAM LEAD
Planner agent, a felted rabbit figurine
PLANNER
Plans · delegates · unifies
routing 12 tasks
Employee file12tasks routed today
plan.graphdelegateschedule
Re-plans when the work changes
Knowledge agent, a felted bear figurine
KNOWLEDGE
Research · reports · memory
indexed 148 docs
Employee file148documents indexed this week
kb.hybridpython.execcite
Answers always cite their sources
Studio agent, a felted cat figurine
STUDIO
Decks · pages · visuals
rendering 1 deck
Employee file23decks shipped this quarter
slides.genimage.chartbrand.kit
On brand, no designer in the loop

Click an employee to open their file

Watch a task become a result.

1

You describe

State the outcome in plain language. That request is the whole spec.

2

Xagent plans

The request becomes steps with owners, tools and order.

3

Tools do the work

Every call, result and metric stays visible while it runs.

4

You keep the agent

Save what worked as an agent your team reuses and schedules.

au.cloud.xagent.co / task
Task · you describe
Tokens
0
Tools
0
Model
deepseek-v3
Preview mock. Live product screenshot to follow.

Not another workflow builder.

Rigid workflows break the moment requirements change. Xagent doesn't follow a fixed diagram. It plans each run, watches the result, and adjusts as the work unfolds.

Drag-and-drop workflow builders

  • Every path drawn by hand, before the work is understood
  • Break the moment requirements change
  • Maintained forever by whoever drew them
  • Or closed platforms in someone else's cloud, taking your data with them

Xagent plans at runtime

  • Describe the outcome. A plain-language goal is the whole spec
  • Xagent plans the steps, and re-plans when reality disagrees
  • Tools do the work, every call and result visible while it runs
  • Keep what worked. Save it as an agent your team reuses
DESCRIBE PLAN EXECUTE RESULT re-plans when work changes

Powered by Xinference.

Run agents on hosted providers, any OpenAI-compatible endpoint, or models on your own hardware through Xinference. Same team, same engine, end to end.

up to 70%lower inference cost than closed-source APIscustomer-reported comparisons
300+open & custom models served through one APIvia Xinference
200+tools your agents can call, plus your own via MCPbuilt in

Inference cost per 1M tokens, indexed

Same workload, three ways to run it
Closed-source API100
Hosted open models55
Self-hosted via Xinference30
Up to 70% lower
Indexed to closed-source API = 100. Customer-reported infrastructure comparisons.
Your monthly model API spend$10,000
Self-hosted via Xinference: about $3,000, keeping $7,000 a month for the roadmap. Illustrative, at the top of the reported range.

Connect the tools you already run.

Native connectors for Google, Microsoft, Meta and LinkedIn. Everything else plugs in through MCP, including your internal systems.

+ any MCP server

Don't start from a blank prompt.

Start from a template, ground it in your data, connect your tools. Then hand the busywork over.

Support chatbot
Inbound leads
LinkedIn post
Email
Content
Inbox manager
Slides
Documents

See all use cases

Your models. Your data. Your infrastructure.

Ship agents into your own products, then run the platform wherever your compliance team needs it.

Widget

Embed Xagent as a chat widget in any product, ready to ship.

API

Call your agents programmatically through a single API.

POST /v1/agents/run

SDK

Make your own app agentic with a few lines of code.

Python · REST

Triggers

Run agents on a schedule or on real-world events, not just prompts.

HostedPrivate cloudOn-premAdmin controlsSSO (OIDC)Run logsTraces & usage

An agent for every job.

Pick a function. Each agent comes with its tools connected, its checks in place, and a planner keeping it coordinated.

Example agents, assembled from Xagent templates, native connectors and MCP tools

Start with one task. Grow into a company platform.

STEP 1

One task

Say what you want done. Xagent plans it, runs it, hands back the result.

STEP 2

Reusable agent

Save the work you keep repeating: role, model, tools, knowledge.

STEP 3

Team of agents

A planner delegates and specialists deliver, with shared context.

STEP 4

Company platform

Shared infrastructure: your models, data and integrations, under your control.

Start small. Scale to the whole company.

Every plan includes unlimited agents and the full platform. Pick the size that fits, then grow into it.

Pro

For getting the first busywork off your desk
$59 /month
  • 2 users
  • 5k actions & triggers / month
  • 10k AI credits included
  • Unlimited agents
  • 3 GB knowledge base storage
  • Bring your own LLM key
Start with Pro
Most popular

Team

For teams that share and reuse agents
$299 /month
  • 10 users
  • 25k actions & triggers / month
  • 50k AI credits included
  • Unlimited agents
  • 15 GB knowledge base storage
  • Bring your own LLM key
  • Priority support
Book a demo

Enterprise

For data boundaries and scale
Contact
  • Unlimited users
  • Unlimited actions & triggers
  • Xagent cloud or self-hosted
  • Bring your own LLM key, or pair with Xinference
  • Knowledge storage on request
  • Admin controls, SSO, run logs & traces
  • Implementation team & training
Talk to sales
Per monthProTeamEnterprise
Price (USD)$59$299Contact
HostingXagent cloudXagent cloudCloud or self-hosted
Actions / triggers5k25kUnlimited
AI credits (LLM)10k50kBYO key
AgentsUnlimitedUnlimitedUnlimited
Users210Unlimited
Knowledge base storage3 GB15 GBOn request
BYO LLM key above credits

A typical agent run uses about 100 credits: a simple task around 5 actions, a complex one around 50.

From the team behind Xinference.

Xagent is built by Xinference, the Australian-owned AI infrastructure company whose inference platform serves 300+ models for banks, insurers and manufacturers worldwide.

Adaptive

Agents plan at runtime and coordinate as a multi-agent team, adapting as work unfolds. Never locked to a brittle flow.

Open

Model-agnostic by design. Run open models or API providers, all connected to your tools through MCP, including your own servers.

Governed

Admin controls, team workspaces, and full run traces built in from day one.

One team, one stack

Your productsWidget, API and SDK put agents inside the tools your company already uses
XagentThe agent platform. Plans, tools, knowledge, teams, governance
XinferenceThe inference engine. 300+ models on your cloud, our cloud, or your own hardware
Your GPUsNVIDIA-optimised serving wherever your data has to live
Australian ownedGlobally trustedNVIDIA optimised

Let's hand something over.

Book a demo on your own workflow, or talk to us about running Xagent inside your product or practice.

Reach us directly

Xinferencexinference.co

What a demo looks like

30 minBring one real workflow. We hand it to agents while you watch.
You keepThe agent we build together, in your workspace.

Book a demo

Stop repeating the same work.

Book a demo on your own workflow. We will hand the busywork to agents while you watch.

Book a demo