aadi-labs/sikaru
Sign up for Sikaru and use it from your coding agent: call catalog models, ask System One decisions, build and publish managed agents, run evals in RL environments, and upload traces.
Write, validate, publish and run a Sikaru managed agent from one Markdown agent document with the Sikaru CLI. Use when the user wants to build, deploy, host, edit, review, publish, test or run a Sikaru agent, give an agent tools, apps or MCP servers, or turn instructions into a hosted agent.
Start here for anything Sikaru. Use when the user mentions Sikaru, sikaru.ai, the sikaru CLI, sikaru_sdk or @aadi-labs/sikaru-sdk, or wants a hosted platform to call catalog models, ask System One decisions, run managed agents, evaluate agents in RL environments or analyze agent traces. Routes to the setup, inference, decision, agent, eval and trace skills.
Ask Sikaru System One choice, yes-or-no and score questions about a text or JSON state, and get answers with probabilities and confidence. Use when the user wants to classify, route, triage, tag, gate or score tickets, messages, documents or app state, or wants a calibrated yes/no instead of free-form LLM output.
Create and version Sikaru RL environment datasets from CSV or JSONL, run an agent against them, and read pass rates and failed examples. Use when the user wants to evaluate, test, benchmark or regression-check a Sikaru agent, build an eval set or golden dataset, compare agent versions, or find out why examples fail.
Call Sikaru catalog models from the CLI or from code with the OpenAI-shaped Python and TypeScript SDKs. Use when the user wants to list or compare Sikaru models, check a model's pricing, context or reasoning settings, chat with a model, stream a reply, or point OpenAI-style code at Sikaru.
Install the Sikaru CLI, sign up or sign in to Sikaru (from the CLI or as an agent through sikaru.ai/auth.md), get a default project, check access, get a project API key for SDK, server or CI use, and add credits. Use when the user wants to get started with Sikaru, create a Sikaru account, log in, or fix "missing credentials", 401, 403 or no-project errors.
Upload agent traces from other systems to Sikaru (OTLP, ATIF or OpenInference spans as JSON or JSONL) and read the trajectory of any run. Use when the user wants to import traces or observability data into Sikaru, debug what an agent did in a run, inspect tool calls and messages, or get traces into Sikaru for evaluation and improvement.