Sapiom is live. We raised $15.75M to build the infrastructure for the next trillion agents. Sapiom is live. We raised $15.75M. Read the story

agent #276,827,931

status: live platform: sapiom

2,053,140running agents
264,394,135tasks running
$66,303,504cost saved
Build agents free
Save cost on agents
sapiom router
$ claude mcp add sapiom --transport http https://api.sapiom.ai/v1/mcp
Your agent cost
Frontier Lab Models Sapiom Router
sapiom runtime
$ npx @sapiom/cli agents run
checklocal
runcloud
inspecttrace
research-briefcompleted

capability providers behind every run

YugabyteDB Anchor Linkup Prelude name.com Polsia

01sapiom router_

One route to what your agent needs.

Call paid capabilities through a typed client or MCP, with access, metering, and attribution carried across the request.

Explore Router
sapiom router remote MCP 
$ claude mcp add sapiom --transport http \https://api.sapiom.ai/v1/mcpsapiom routerremote MCP https://api.sapiom.ai/v1/mcpcatalog capability toolsdiscover tool_discover
Search Scraping Models Images Audio Browser Compute Data Messaging Files

02agent.studio_

Build the workflow in one place.

Work with a real coding agent, then move between Canvas, Steps, and Code as the workflow takes shape.

Explore agent.studio

03sapiom runtime_

Wait, resume, and stay inspectable.

Deploy typed step graphs with explicit retries, signals, schedules, and per-attempt traces.

Explore Runtime
sapiom runtimerecent runs
Agent Service Cost Status
research-brief email metered Completed
research-brief ai model access metered Completed
research-brief web scraping metered Completed
research-brief search the web metered Completed
competitor-watch email metered Completed
competitor-watch web scraping metered Completed

one command connects everything

Your first agent, running in minutes

Start in your coding agent, terminal, or agent.studio. Sapiom handles the setup.

01

Start from a template

Clone a workflow and run it locally.

02

Bring your own agent

Check, link, and deploy the TypeScript you have.

03

Start from intent

Describe the job and scaffold a typed workflow.

Start building free Browse templates 
/plugin marketplace add sapiom/sapiom-js
/plugin install sapiom

Registered the sapiom-dev MCP server.
Added the sapiom-agent-authoring skill.
Run sapiom_authenticate once to sign in.

from local graph to managed run

One workflow, through the full loop.

One capability interface

Call paid capabilities through ctx.sapiom, MCP, or @sapiom/tools, with usage metered at call time.

Browse published rates

Managed runs stay inspectable

Deploy typed step graphs, schedule or signal them, and inspect every recorded attempt.

Explore Runtime

Plan the deployment together

Bring volume, security, procurement, and support requirements to the Sapiom team.

Book a demo

The new way to build agents.

Agents are brilliant, but powerless. Money is the universal API key.
Ilan ZerbibFounder and CEO, Sapiom
If you really think about it, every API call is a payment.
AK Amit KumarPartner, Accel
The next trillion buyers will not be human.
Sapiom launch post6 February 2026

from the blog

What we shipped, and why.

6 February 2026

Sapiom raises $15.75M to build the infrastructure agents run on

The seed round, led by Accel, and the thesis behind it: the next trillion buyers will not be human.

Read the story 11 June 2026

Sapiom acquires Fewsats

Machine-native payment rails move inside the execution layer, so an agent can pay for what it needs mid-run.

Read the story

Questions, answered.

Scaffolding, offline graph validation, and local runs with stubbed Sapiom capability calls are free and work signed out. The moment a run calls a real capability, it is metered.

sapiom_dev_agents_run_local

In a private git repository Sapiom provisions and you own. It is ordinary TypeScript built on @sapiom/agent, so you can read it, review it, and take it with you.

npm install @sapiom/agent

Claude Code, Codex, Cursor, Claude Desktop, and any client that speaks MCP over stdio. Hosted clients that cannot run npx, including ChatGPT, use the remote server over HTTP.

claude mcp add sapiom -- npx -y @sapiom/mcp

Sapiom carries agent and trace context with capability calls, so usage can be attributed back to the work that produced it. Recent executions and their step attempts are available through the CLI.

npx @sapiom/cli agents logs

No. Search, scraping, models, compute, storage, email, domains, and the rest arrive through one integration. Sapiom holds the vendor relationships and meters the calls back to you at published rates.

claude mcp add sapiom --transport http https://api.sapiom.ai/v1/mcp

Start with a local run.

Scaffold the workflow, validate its graph, and execute real step code with local stubs for Sapiom capability calls.

Start building free Save cost on agents