Create sandboxed rich-text telegram agents with a single config file

A new open-source tool allows developers to create sandboxed Telegram agents with rich-text formatting using a single YAML config file. Built on Deno, the tool supports customizable system prompts and granular sandbox permissions for network, filesystem, and environment access. The agent uses Claude models and can execute JavaScript in a restricted subprocess, enabling diverse use cases like research paper readers or coding assistants.

create sandboxed rich-text telegram agents with a single config file needs deno https://deno.com/ . deno task start my-agent.yaml this example is a research paper reader: name: my-agent telegram token: "123456:ABC-DEF..." anthropic api key: "sk-ant-..." allowed usernames: - your-username model: claude-opus-4-8 optional system: | optional — defines what the agent is you are a research paper reader assistant. download all html papers you read and store them. when embedding a figure, only use real image urls from arxiv.org. sandbox: optional — omit to deny all net: "arxiv.org" hosts, not urls write: "./papers" env: false required: telegram token , anthropic api key , allowed usernames . the system prompt is what turns the same engine into a paper reader, a maps helper, a coding assistant, etc. — telegram formatting and the agent's sandbox permissions are explained to it automatically, so system only needs the persona. the yaml holds secrets. don't commit it. the agent's one tool is run javascript , which runs in a deno subprocess. each sandbox entry maps to a deno --allow- flag on that subprocess: true → allow unrestricted list → allow only those hosts/paths e.g. --allow-net=a.com,b.com false / omitted → denied omit the whole sandbox block and generated js gets zero permissions. denied operations fail with a deno permission error returned to the agent. the agent is told its exact permissions in its system prompt, so it knows what it can and can't do. replies are sent with telegram's sendRichMessage , so the agent's github-flavored markdown renders natively: headings, bold / italic , ~~strikethrough~~, lists, task lists, blockquotes, code , fenced code blocks, links, footnotes, latex formulas $x^2$ , tables, and media blocks url , including maps via <tg-map .../ . a bad media url is stripped and the message is retried so formatting never gets dropped wholesale. - typing indicator while it works - native rich-text replies graceful fallback - per-user conversation history in memory, resets on restart - streamed under the hood so long replies don't time out deno task test