karta
// platform

Deploy your agents as dedicated AI specialists.

Bring any model, harness, and agent project. Karta runs it as durable, governed specialists for users, teams, and jobs on a secure, scalable cloud - ours or yours - with tenant data isolation, crypto-shredding, and customer-managed keys.

L7
Agent Products
what you ship
Customer support agent SaaS copilot AI tutor Virtual employee Backend automation
L6
Specialist Distribution
distribute / use your agent
surfacesweb embed widget · session API · React SDK · scheduled runs · backend jobs
includeswidget customization + theming · per-end-user metering + analytics · multi-layered hard spend limits · connector + model routing · multi-tenant white-label
L5
Managed Agent Platform
run your agent
Karta Cloud or Your own cloud or On-prem
includesrun any harness natively · durable, isolated specialists for users, teams + jobs · verified end-user identity · per-boundary memory + files · releases + rollback · tenant data isolation + crypto-shredding · BYOK + customer-managed keys · governance, audit + approvals
karta
L4
Agent Project
harness engineering
configure your harness with skills, MCP, hooks, subagents
useharness-native format, e.g. CLAUDE.md + .claude/ for Claude Code
L3
Agent Harness
select one harness
Claude Code OpenCode Deep Agents Goose Codex CLI Bring your own harness
L2
Agent runtime / sandbox
isolated execution
Fully isolated per-session runtime
managedprovisioned and operated by Karta
L1
Model
select one model family
Anthropic OpenAI Google Open-source Bring your own key Bring your own model
solid = supported today dashed = you bring
// L5 · managed agent platform

Run your agent.

The managed platform runs your agent project in any harness as durable specialists for users, teams, and jobs, with the controls to operate them in production.

Any harness, run natively

Claude Code, OpenCode, DeepAgents, Goose, Codex CLI, and other supported harnesses, in their native project format. Karta does not translate your agent into a proprietary workflow graph.

Durable, isolated specialists

A persistent workspace plus per-session isolated execution for each user, team-owned worker, or backend job. Files and artifacts survive the next session and the next release.

Verified end-user identity

Every user-facing specialist is bound to a verified end-user, so memory, files, and spend attribute to the right person rather than a shared key.

Native releases and rollback

Karta freezes the source, harness, environment, and network contract into an auditable release, and rolls back on demand.

Enterprise data controls

Per-organization data isolation, advanced crypto-shredding, bring-your-own cloud, and bring-your-own and customer-managed keys.

Governance, audit, approvals

Audit logs, role-based access, and human approval steps for the actions an agent takes on your behalf.

// L6 · specialist distribution

Ship it to users, teams, and jobs.

Karta distributes your specialists across surfaces and meters the people, teams, jobs, and tenants they serve.

Multi-surface serving

A web embed widget, a session API, a React SDK, scheduled runs, and backend jobs, all from one agent.

Widget customization

Theme and configure the embedded agent surface to match your product, including multi-tenant white-label.

Per-end-user metering

Usage attributed to each end-user, organization, model, and session, so you can see and package what every user costs.

Multi-layered hard spend limits

Hard caps per end-user and per organization, enforced before a bad run or a leaked key creates a surprise bill.

Connector and model routing

Route each turn to the model or connector you choose, with your own keys or the platform default.

One agent, many specialists

Serve many tenants from a single agent project, each with isolated identity, memory, and spend.

// enterprise controls

Who owns what.

Karta provides the platform controls; you configure the boundaries for your data and users.

Control Karta provides You configure
Data isolation Per-organization data-plane isolation Which organizations and tenants are separated
Encryption Advanced crypto-shredding with per-store keys Bring your own key and customer-managed keys
Deployment Managed cloud, or run the data plane yourself Karta Cloud, your own cloud, or on-prem
Identity Verified end-user identity model Your identity provider and token issuance
Spend Multi-layered hard spend caps Per-user and per-organization limits
Audit Audit log, role-based access, approvals Review policy, export, and access grants

Run your agent on Karta.

Read the docs to bring your first agent project, or join the waitlist.