Unified agent command center
Build, run, and govern AI agents from a single platform rather than managing separate tools for orchestration, access, and oversight.
Kortix
ReivindicarKortix is an open-source AI command center to build, run, and govern AI agents in one place, with flexible plans and deployment options.
Overview
Kortix is an open-source AI command center for companies that want to build, run, and govern AI agents in one place. The site positions it as a platform for connecting agents to tools and models while keeping access, policy, and change management under control.
The pricing and enterprise pages describe a platform that combines agent runtime, model access, and governance. Teams can start with a free sandbox tier, move to a Team plan with pooled usage credits and managed frontier models, or adopt Enterprise for SAML SSO, SCIM, advanced RBAC, audit logs, and Cloud, VPC, or on-prem deployment.
Features
Tool and integration access through a single token
The pricing page says the product connects 3,000+ tools, and the enterprise page describes connectors, models, and integrations being proxied through one token.
Permission controls for agent actions
Use allow, ask, and block rules per action, including network-level patterns, so each agent only reaches the systems it needs.
Git-based policy and configuration
Keep policies, agents, and configuration in one `kortix.toml` inside a Git repository, with changes represented as diffs that can be reviewed and reverted.
Enterprise identity and governance
Support sign-in and enterprise directory control with SAML SSO and SCIM, plus advanced RBAC and audit logs on the Enterprise plan.
Flexible model and compute options
Choose the runtime and commercial model that fits the team, including free sandbox credits, team usage credits, BYOK, ChatGPT subscription support, and managed frontier models.
Use Cases
Company-wide agent operations
Centralize agent workflows when a company needs one place to create agents, connect them to tools, and govern how they operate.
Team deployment and shared usage
Use pooled credits and team seats when a group needs to run ongoing agent work without managing separate billing for each project or user.
Governed enterprise rollout
Adopt enterprise controls when security teams need SSO, directory sync, RBAC, audit logs, and deployment options beyond a standard cloud setup.
Early testing and proof of concept
Use sandbox credits and a free project to evaluate the platform before committing to a paid deployment.
Model-choice workflows
Connect preferred models through BYOK or a ChatGPT subscription when teams want to keep existing model relationships while using Kortix for agent orchestration.
Pros and Cons
Pros
- Combines agent building, runtime, and governance in one product.
- Supports team usage with pooled credits and seat-based pricing.
- Offers multiple model access paths, including BYOK and ChatGPT subscription support.
- Provides enterprise controls such as SAML SSO, SCIM, RBAC, and audit logs.
- Supports deployment choices that include Cloud, VPC, and on-prem.
Cons
- The provided pages do not include a detailed feature reference or connector catalog, so specific integrations are hard to verify from source alone.
- Pricing details are split across free, team, and enterprise messaging, which means readers may need to contact sales for a full enterprise quote.
FAQ
What kind of product is Kortix?
Kortix presents itself as an open-source AI command center for companies. The pricing page indicates a Free plan, a Team plan, and an Enterprise option.
How does Kortix pricing work?
The pricing page says Free includes sandbox compute credits and 1 project. Team includes pooled usage credits per seat, managed frontier models, and support for more projects and seats. Enterprise adds SAML SSO, SCIM, advanced RBAC, audit logs, and deployment options such as Cloud, VPC, or on-prem.
How is Kortix organized for teams?
The enterprise page says the control plane lives in one Git repo, with policy, agents, and config stored in one `kortix.toml`. Changes are tracked as commits and diffs.
How does Kortix handle access and secrets?
The enterprise page says connectors, models, and integrations are proxied through a single Kortix token, and each agent gets only the tools, secrets, and files it needs.
What should I verify before adopting Kortix?
The source does not show a full feature walkthrough or supported-tool catalog, so the exact integration coverage and setup flow are not fully documented in the provided pages.
Quick Facts
- Category
- AI command center
- Source domain
- kortix.com
- Positioning
- Open-source platform for building, running, and governing AI agents
- Pricing model
- Free, Team, and Enterprise plans
- Deployment
- Cloud, VPC, or on-prem on Enterprise
- Governance
- SAML SSO, SCIM, RBAC, and audit logs on Enterprise
Alternativas ao Kortix
Kastra
Kastra authorization infrastructure for AI systems checks prompts, tool calls, shell commands, API requests, and browser actions before execution.
Orca
Orca is an Agent Development Environment for shipping with coding agents, running multiple CLI agents in parallel across isolated worktrees, with desktop and mobile workflows.
AI Magicx
AI Magicx is a unified AI workspace for chat, image, video, voice, music, email and developer tasks, helping teams and creators manage multiple models in one place.
Paper
Paper is a design tool that connects canvas, code, and AI agents so teams can create, share, and ship work in one workflow. Includes desktop app and MCP access.
blop
blop is a QA agent that writes browser tests as code in your repo, runs them in CI, clusters repeated failures, and can open PRs to fix broken tests.
RLAMA
RLAMA is a local AI platform for building RAG systems and intelligent agents on macOS, Linux, and Windows, with HTTP API support.