# Sikaru

> Self-improving managed agents. Sikaru runs agents in the cloud, serves their models, reads every run, and improves each agent through tested changes to its context, harness, or post-trained weights, with a person approving every release. Create managed agents from instructions, connect shared resources, publish a reviewed version, and watch conversations as they run.

## Start here

- [Agent authoring guide](https://sikaru.ai/agent-guide.md): Three worked documents, mention grammar, create-first CLI journey, Go live, and hosted CLI/curl/Python/TypeScript snippets.
- [Installable authoring skill](https://sikaru.ai/skills/author-sikaru-agent/SKILL.md): Coding-agent authoring workflow.
- [Frontmatter JSON Schema](https://sikaru.ai/schemas/agent-document.json): Validate the YAML object; the server also validates resources and project ceilings.
- [Full reference](https://sikaru.ai/llms-full.txt): Product boundaries and integration paths.
- [Integration skill](https://sikaru.ai/SKILL.md)
- [Documentation](https://docs.sikaru.ai)
- [Platform](https://sikaru.ai/platform): Authenticated workspace.
- [Request access](https://sikaru.ai/request-access)

## Writing

- [Self-improving managed agents, steered by your team](https://sikaru.ai/blog/self-improving-managed-agents.md): Teams running agents end up building a research lab one tool at a time. Sikaru is that lab, with your team's judgment in it. Now in private beta.
- [Introducing Sikaru: self-improving agents, with the lab built in](https://sikaru.ai/blog/introducing-sikaru.md): The inference-native platform where managed agents learn from every production run, with a built-in lab that ships tested updates to their context, harness, and weights.

## Current authoring capabilities

An agent is one Markdown document. Create it through the public managed-agents
operation with sourceKind agent_document and exact document text. Native agents
pull/push/validate/publish/snippets commands operate on an existing identity.
Shared app and MCP connections are named in body mentions. Built-ins default on
within project ceilings. Saving does not publish; Go live publishes the reviewed
draft. Shared secrets use per-session placeholders in the managed sandbox, with
header-only substitution to allowed HTTPS hosts and per-request approvals when
required. Local compute receives no secret placeholders. Studio Test saves edits,
pins the requested Draft revision, and runs as the signed-in tester with separate
memory and workspace. Public execution-sessions accepts environment draft and
draft_revision; acknowledge widening after review. Signed-in users connect personal accounts and resume the same turn. Agent schedules target agent_slug and production, follow the Live version and sealed access per occurrence, and expose history and notices through run-schedules. Fresh conversations are the default; persistent conversations rebase safely. Personal scheduled calls require the creator to have published the Live version.

Use returned hosted snippets to create an execution session, append a turn, and
stream events. Never invent credentials or treat a queued turn as a final answer.