Docs

Read-only search over the public Sikaru documentation: managed agents, inference, evals and traces.

LLM Mart 1 views 159 listing impressions

Sikaru is a managed agent runtime. Users define an agent and send it work; Sikaru runs it and returns results, events, and execution evidence. It can be used for a support assistant, a research agent, or an operations agent.

Users can integrate execution via a Dashboard, SDKs, or REST API in Python or TypeScript. The backend authenticates with a Sikaru project API key, and no model-serving credentials are needed. Traces from agents already running elsewhere can be submitted without moving execution.

A session is one conversation that keeps its own context and pins one release.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Read and write RAGE Package Format archives

23 views

Let LLM help you achieve your regression analysis with Stata

21 views

Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.

21 views

vSphere with Tanzu (VKS): Namespace and TanzuKubernetesCluster lifecycle. Requires vSphere 8.x+.

20 views