Deploy Now

SaaS Alternative

Devin Claude Cowork ChatGPT Work

Categories

Developer Tools Automation LLM Workflow Automation AI Agent Enterprise AI AI Management

Stars

20,159

Forks

3,432

Watchers

153

Developer links

Last Updated: 08-30-2026
Share on X

Kortix

Kortix Suna is an AI management system where autonomous agents run on isolated Linux sandbox computers, producing finished deliverables that humans review through a change request workflow before anything merges. With 20,000+ stars, it positions itself against Claude Cowork and ChatGPT Work by storing every agent persona, skill, memory artifact, and connector in a git repository: versioned, diffable, and shared across an organization. Each session launches a dedicated sandbox with full terminal access, Playwright-controlled Chromium, writable filesystem, and internet connectivity. Over 3,000 app connectors are available through MCP, OpenAPI, GraphQL, and raw HTTP, with credentials brokered server-side so tokens never enter the sandbox. Skills (reusable markdown-plus-script packages encoding company workflows) load automatically into every session, compounding institutional knowledge over time. Bring-your-own-key model routing through LiteLLM connects to OpenAI, Anthropic, Google, Mistral, or local models without vendor lock-in. The deployment runs as a single Docker Compose stack bundling the Next.js frontend, FastAPI backend, Supabase, Redis, and Caddy with automatic TLS certificates. Enterprise features include SAML/OIDC SSO, SCIM provisioning, RBAC, and audit logging. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0.

Kortix
Kortix
Kortix
Kortix
Kortix

Benefits

  • Git-Versioned Agent Configuration
  • Every agent persona, skill definition, memory artifact, and connector credential lives in a git repository with full version history, diff tracking, and branch-based isolation per session.
  • Isolated Sandbox Cloud Computers
  • Each agent session runs on a dedicated Linux sandbox with terminal access, Chromium browser, writable filesystem, and internet connectivity, preventing cross-session data leakage and ensuring reproducible execution.
  • 3,000+ App Connectors
  • Connect to thousands of applications through one-click integrations, MCP servers, OpenAPI specifications, and GraphQL endpoints, with credentials brokered server-side through scoped tokens.
  • Human-Approved Change Requests
  • Agents produce deliverables on isolated branches and submit change requests for human review before merging, providing governance and audit trails for every action taken.

Features

  • Multi-Provider LLM Routing
  • Bring your own API keys for OpenAI, Anthropic, Google, Mistral, or self-hosted models, routed through LiteLLM with cost tracking and automatic fallback.
  • Reusable Skills System
  • Markdown-plus-script packages encoding company workflows compound institutional knowledge and automatically load into every agent session for consistent task execution.
  • Docker Compose Self-Hosting
  • Single command deploys the full stack (Next.js frontend, FastAPI backend, Supabase, Redis, and Caddy) on any VPS with automatic TLS certificates.
  • Web Browsing and File Management
  • Integrated Playwright-controlled Chromium browser navigates websites autonomously, while full filesystem operations handle creating, reading, modifying, and organizing content.
  • Enterprise SSO and RBAC
  • Optional enterprise features include SAML and OIDC single sign-on, SCIM directory provisioning, role-based access control, and comprehensive audit logging.