“Telegram”

Self-hosted AI agent built on n8n, PostgreSQL and Claude that runs over Telegram or a webhook API.

Ops agent that finds the root cause of infrastructure problems, can fix them, and runs from Slack, Telegram or Lark

Runs a Claude Code dev team on your server and drives it from Telegram, VK or LO chats, opening a PR per request.

Open-source terminal coding agent for the xAI Grok API with headless and Telegram control.

Claude Code agent on a VPS you own, with a real Chromium browser and a Telegram bot to message it.

Always-on personal agent that turns Telegram voice notes into linked markdown notes in your Obsidian vault on a VPS.

Agent that turns a goal in plain words into planned, built and tested work, reachable from Slack and Telegram

Personal AI assistant with eight memory types, hourly proactive check-ins and channels from macOS and iOS to Slack and Telegram.

Self-hosted agent from Nous Research that builds skills from experience and is reachable from the terminal and chat apps

Lightweight self-hosted personal agent framework in Python with a WebUI, chat-app channels, memory and MCP

Self-hosted agent that gives each assistant its own virtual machine and a patched Firefox browser for web tasks

Stateful agent harness whose agents keep memory across sessions and run on schedules through a CLI, browser and chat apps.

Open-source single-binary personal agent server in Rust with sandboxed commands and chat channels.

Proprietary desktop and mobile AI agent that runs on your computer, works toward a goal in the background and uses 15+ model providers.

Local-first agent OS that runs Claude Code, Codex and OpenCode on your machine and lets you drive them from a browser or chat apps.

Free desktop app that runs Claude Code, Codex, Gemini, Grok and local agents in parallel, with automations, schedules and a Kanban board.

Open-source DevOps agent that runs 24/7 on your own machines, works on schedules and messages you only when it needs a person.

Cloud coding agent that runs your own dev environment, reviews its work with a second model and opens PRs with live previews.