Does Onecortex provide the model?
Does Onecortex provide the model?
No. Your agent calls the model provider you choose, with its API key added as a secret. Onecortex runs your agent, not a model.
Which languages and frameworks are supported?
Which languages and frameworks are supported?
Python 3.12 and 3.11, and TypeScript or JavaScript on Node.js 22 and 20. LangGraph, the OpenAI Agents SDK, Strands Agents, CrewAI, LangChain and LlamaIndex in Python; Mastra, the Vercel AI SDK and LangChain.js in TypeScript; and any agent at all as a plain function. See Entrypoints.
Can I bring my own Dockerfile?
Can I bring my own Dockerfile?
No, by design. Onecortex builds the image from your dependency file so that every agent gets the same tested runtime, and so that a build can be smoke tested the same way every time.
systemPackages and build.commands cover most needs. See Python agents.Do I need to write a server?
Do I need to write a server?
No. Point
entrypoint at your agent object, and Onecortex serves it. A server started at import time fails the build. See Entrypoints.Does Onecortex write to my repository?
Does Onecortex write to my repository?
Never. The GitHub app has read only access, and your source is never modified. See Security.
Can I host an MCP server?
Can I host an MCP server?
No. Onecortex hosts agents. Your agent can call MCP servers, and calling your agent from MCP clients is coming: see MCP.
Are there traces or token usage?
Are there traces or token usage?
Not yet. Your agent’s logs and the event stream, with every tool call and step, are how you see what a run did.
What does it cost?
What does it cost?
Nothing, during the private beta. See The private beta.
Where does my agent run?
Where does my agent run?
In Europe (Frankfurt). See Regions.
What happens to my live agent if a build fails?
What happens to my live agent if a build fails?
Nothing. It keeps serving the version that was live. A new version goes live only after it has passed its smoke test. See Builds.
Does my agent remember conversations?
Does my agent remember conversations?
Only what it keeps itself. Calls with the same
sessionId reach the same running instance, so in memory state survives between them for a while. See Sessions.Can I use a custom domain?
Can I use a custom domain?
Not yet. Every agent is called at
https://api.onecortex.io.