cycls.com valid

Cycls

The deep-stack AI SDK for Python. Runtime, interface, intelligence and state as composable primitives, in one file, deployed with one command.

For agents: Python AI SDK for building and deploying agents in one file with one command; docs cover quickstart, functions, images, volumes and core concepts.

python sdkai agents deploymentdockerserverlessquickstartllm runtime

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-24T05:38:00.052Z. Cached copy · Source on cycls.com

# Cycls

> The deep-stack AI SDK for Python. Runtime, interface, intelligence and state as composable primitives, in one file, deployed with one command.

- [Introduction](https://docs.cycls.com/get-started/introduction.md): Cycls is the deep-stack AI SDK for Python. Runtime, interface, intelligence and state are composable primitives in one file, deployed with one command.
- [Quickstart](https://docs.cycls.com/get-started/quickstart.md): Install Cycls, run an agent on your machine, then deploy it to a public URL.
- [Core concepts](https://docs.cycls.com/get-started/concepts.md): The mental model behind Cycls: three layers, four builders, and three verbs.
- [Functions](https://docs.cycls.com/build/functions.md): Turn any Python function into a container that runs on your laptop, in the cloud, or on a schedule, without writing a Dockerfile.
- [Images](https://docs.cycls.com/build/images.md): Declare pip packages, system libraries, bundled files and build commands in Python. Cycls hashes the result into a cached Docker image.
- [Volumes](https://docs.cycls.com/build/volumes.md): Named persistent storage you attach to any deployment at any mount path. Data outlives the deployments that use it.
- [Cron](https://docs.cycls.com/build/cron.md): Add one argument to a function and the platform calls it on a schedule. No scheduler to run, nothing to drift.
- [Apps](https://docs.cycls.com/build/apps.md): Return a FastAPI application and get a URL, sign-in, and per-user storage. Everything a function can do, an app can do too.
- [Agents](https://docs.cycls.com/agents/overview.md): A chat product in one decorator: managed LLM loop, tools, files, history and a web interface.
- [Models](https://docs.cycls.com/agents/models.md): One builder for every provider: Anthropic natively, and any OpenAI-compatible endpoint through a base URL.
- [Tools](https://docs.cycls.com/agents/tools.md): Enable built-in tools by name, or register your own Python handlers. Both stream into the same UI.
- [Streaming components](https://docs.cycls.com/agents/streaming.md): Yield strings for markdown or dicts for rich components: thinking bubbles, tables, code, callouts, images and client actions.
- [Context](https://docs.cycls.com/agents/context.md): Every turn hands your agent a context object with the conversation, the user, the workspace and the switches that user set.
- [Instructions and skills](https://docs.cycls.com/agents/knowledge.md): Give an agent standing instructions it reads every turn, and skill packs it loads only when the task calls for them.
- [Files and the canvas](https://docs.cycls.com/agents/files.md): Every user gets a workspace of files. The canvas renders spreadsheets, documents, slides, PDFs, images and HTML without leaving the chat.
- [Connectors and MCP](https://docs.cycls.com/agents/connectors.md): A user connects an account once, and the tools that need it get a live credential. OAuth, pasted keys, private endpoints and remote MCP servers.
- [Sandbox and tr
…

Related sites

Find similar publishers by meaning →

Other listed sites in AI agents and MCP. See the whole category →

Machine-readable: GET /v1/resolve?q=cycls.com · GET /v1/domain/cycls.com · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for cycls.com:
1. POST https://agentwebmap.com/v1/sites/cycls.com/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://cycls.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/cycls.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/cycls.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.