#1414th of 19 in Agent platforms
suna
Git-repo-based agent platform running each session in its own cloud sandbox
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 20.3k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
Kortix keeps agents, skills, memory, connectors and triggers as files in a git repo (kortix.yaml). Each session runs an OpenCode agent in an isolated sandbox on its own branch, and its work reaches main only through a change request a person approves. It is used from the web app, CLI, Slack and Microsoft Teams, with cron and webhook triggers. Self-hosting uses a Docker Compose stack started by the CLI.
Who it is for: Teams wanting self-hosted, governed cloud agents as a Claude Cowork alternative
Strengths
- Per-session sandbox on its own branch; merge to main needs human approval
- Per-tool Allow/Ask/Block rules, audit trail, SAML SSO and SCIM
- Any model provider with your own keys; config lives in git
- Slack and Teams channels, cron and signed webhook triggers
Weaknesses
- License reported as NOASSERTION; terms need checking before commercial use
- Self-host setup asks for integration credentials for managed git, GitHub and Pipedream
- Self-host pulls images from Docker Hub, so it is not an offline install
- Default provider isolates with containers; microVMs only on the Platinum provider
What it needs
- no GPU
- Needs Docker, Docker Hub, Pipedream, GitHub
- Models: Any provider with your own API keys, ChatGPT subscription
Also in Agent platforms
See all 19| Rank | Project | Score |
|---|---|---|
| 1 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 80 out of 100 |
| 2 | daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps | 78 out of 100 |
| 3 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 75 out of 100 |
| #4 | deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks | 75 out of 100 |
| #5 | MulticaIssue board where AI coding agents take assignments like teammates | 73 out of 100 |