agentafk

5.0 0 reviews
0 Views 2026-09-21
Visit site

About This Site

Open-source runtime for safely running coding agents without constant supervision Agent AFK is an open-source, local-first runtime for running coding agents unattended. It allows developers to start coding tasks, walk away, and later review verified results through traces, terminal states, and receipts of agent activity. The runtime supports permission boundaries, reversibility gates, isolated worktrees, parallel subagents, adversarial verification, persistent session memory, and Telegram supervision. It works with Claude, Cursor, Claude Code, Codex, custom agents, and other model providers while keeping the runtime and data on the user's machine.

Alternatives

Key Features AI

Core Features
Unattended coding-agent execution with daemon and background workflows
Permission boundaries, reversibility gates, isolated worktrees, and risk-aware actions
Parallel subagent orchestration with coordinated interruption
Adversarial verification and self-checking before changes are accepted
Complete local trace history for sessions, subagents, and tool calls
Explicit terminal states including Done, Blocked, Asking, and Interrupted
Telegram supervision for notifications, responses, redirection, and interruption
Composable slash skills such as /mint, /diagnose, /review, /shadow-verify, and /ship
Persistent plans, preferences, conventions, decisions, and session memory
Support for external and local model providers through a BYO-model approach
Advantages
Open-source and Apache-2.0 licensed
Free runtime with all core features included
No account required
Runs locally with support for macOS and Linux
Works with multiple model providers, including local models
Provides detailed traces and visible tool calls for accountability
Includes verification workflows instead of relying only on agent claims
Supports remote supervision through Telegram
Uses isolated worktrees and reversibility-aware controls to reduce blast radius
Persistent plans, memory, and recovery paths help manage long-running tasks
缺点:Requires Node.js 20 or newer and command-line setup
缺点:Currently positioned primarily for macOS and Linux users
缺点:Users must provide and pay for their own model usage
缺点:Configuring agents, Telegram, repositories, and custom workflows may require technical expertise
缺点:The paid support plans are expensive for individual developers
缺点:Autonomous coding still requires human review before risky changes are shipped
缺点:Performance and output quality depend partly on the selected model provider

agentafk Reviews (0)

5.0 0 reviews
  • No reviews yet. Be the first to write one!

30-Day Click Trend

08-23 09-06 09-21

Related Sites

AI-powered platform for business acceleration, enhancing hiring, collaboration, and productivity. Samespace is an AI-powered business acceleration platform that offers a suite of products designed to enhance hiring, collaboration, interactions, and team productivity. It provides tools for automating hiring processes, improving customer experience (CX), tracking productivity, and enabling collective intelligence within teams.
Local-first AI workspace for creating, editing, and managing business documents. Sofos is a local-first desktop workspace for business teams that combines a Markdown document editor with a Claude-powered agent in the same window. Users can work with files such as Markdown, HTML, PDF, and CSV, ask the agent to read and edit documents, connect business tools through integrations, and review changes tracked in Git. Sofos is designed for creating and managing PRDs, briefs, decks, reports, plans, summaries, and other business documentation without using a terminal.
MindsDB: AI data automation solution connecting enterprise data for real-time decision-making using SQL. MindsDB is an Enterprise Data Platform for AI that enables users to apply the power of OpenAI's GPT-3 and Hugging Face models to the text data in their database using simple SQL commands. It allows for automatic classification, labeling of text columns, message creation, summarization, translation, and more. MindsDB connects and unifies petabyte-scale enterprise data, enabling enterprise-wide informed decision-making in real-time. It operates as a cognitive engine that can operate anywhere, understands complex questions in the context of organizational data, retrieves knowledge across structured and unstructured data platforms, delivers actionable insights, provides transparency into its thinking process, and ensures data privacy.
Create custom AI agents to automate browser tasks with no API costs. Browseragent is a platform that allows users to create custom AI agents that run directly in their browser. These agents can automate repetitive browser tasks without requiring API costs or maintenance, ensuring full privacy. It enables building powerful automations in minutes using an AI-powered workflow builder.
AI Chrome extension that records browser workflows and turns them into ready-to-run automations. Spion is a free Chrome extension that records repetitive browser workflows, analyzes them with AI, and converts them into ready-to-run automations for tools like Claude, Workato, Make, Zapier, and n8n, as well as step-by-step PDF guides. It operates without code by identifying patterns in manual browser tasks, such as copying data between spreadsheets, CRMs, and communication tools, and optimizes them into cleaner, automated workflows that run without a literal replay of clicks.
Always-on cloud desktops for AI agents with browsers, email, and live control vpsai.ai is MyClawn's AI VPS platform, providing an always-on cloud computer designed for AI agents. Each machine includes a persistent Linux desktop, Chrome browser, files, terminal, dedicated email address, live screen streaming, and remote keyboard and mouse control. Users can assign work to the built-in chat-driven agent, monitor tasks from any device, take over for CAPTCHA or two-factor authentication, and return control to the agent. Plans include AI usage credits, persistent storage, and a dedicated cloud machine.