Is agent-afk open source?

Yes, licensed under Apache-2.0.

agent-afk

Active·★ 56·Apache-2.0·Updated 2026-10-08

★ Hidden Gem

Agent AFK is an open-source, customizable coding agent harness designed for long-running development tasks, offering full control over its behavior, prompts, and tools. It allows users to run agents with various models, edit operational rules, and manage persistent memory across sessions.

#Coding Agent#LLM Orchestration#Customizable AI#Developer Tool#Persistent Memory#CLI#Workflow Automation#Node.js

Features

01Customizable Agent Loop: Users can edit prompts, gates, routing, and skills, gaining full ownership and control over the agent's behavior.

02Headless Daemon Operation: Enables running long-duration coding tasks in the background, with optional notifications via Telegram upon task completion.

03Cross-Session Persistent Memory: Agents maintain preferences, decisions, and procedures across runs using both hot memory (for always-present facts) and a searchable fact archive.

04Built-in Task Orchestrators: Provides high-level commands like `/mint` for full feature development and `/diagnose` for automated bug root-cause analysis, dispatching waves of subagents.

05Multi-Surface Interaction: Supports interaction via one-shot commands, an interactive REPL, a headless daemon, and a Telegram bot, all sharing the same session manager and memory.

Compatibility

Node.js

Runtime

Verified via docs

Anthropic

LLM Provider

Verified via docs

OpenAI

LLM Provider

Verified via docs

Ollama

LLM Provider

Verified via docs

LM Studio

LLM Provider

Verified via docs

Quick start

$ npm install -g agent-afk

Use cases

↳Automating lengthy coding projects: Delegate complex, multi-step coding tasks to run autonomously in the background.

↳Interactive terminal-based development: Use the REPL for real-time coding assistance, tool access, and plan mode, integrating directly into the developer's workflow.

↳Full feature development lifecycle: Orchestrate the entire process from idea (spec) to research, planning, building, verifying, and shipping new features using `/mint`.

↳Automated bug diagnosis and resolution: Employ `/diagnose` to automatically generate and test multiple root-cause hypotheses for failing tests or bugs.

↳Personalized agent knowledge management: Maintain and leverage a persistent memory of preferences, decisions, and procedures across all agent interactions.

Alternatives

OpenClaw★ 391.5k

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

MindsHub (formerly MindsDB)★ 39.8k

MindsHub (formerly MindsDB) is an agent workspace for knowledge work and software development, with connected data sources, a model router across frontier and open models, open-source agent harnesses, and publishable artifacts.

Microsoft AutoGen★ 61.3k

A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

Gemini CLI★ 107.3k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

nanobot★ 48.9k

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

letta★ 25.1k

Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.

sre★ 1.3k

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

firecrawl-mcp-server★ 7.6k

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

See all alternatives →

Comments

No comments yet. Be the first!

agent-afk

Active·★ 56·Apache-2.0·Updated 2026-10-08

★ Hidden Gem

#Coding Agent#LLM Orchestration#Customizable AI#Developer Tool#Persistent Memory#CLI#Workflow Automation#Node.js

Features

01Customizable Agent Loop: Users can edit prompts, gates, routing, and skills, gaining full ownership and control over the agent's behavior.

02Headless Daemon Operation: Enables running long-duration coding tasks in the background, with optional notifications via Telegram upon task completion.

03Cross-Session Persistent Memory: Agents maintain preferences, decisions, and procedures across runs using both hot memory (for always-present facts) and a searchable fact archive.

04Built-in Task Orchestrators: Provides high-level commands like `/mint` for full feature development and `/diagnose` for automated bug root-cause analysis, dispatching waves of subagents.

05Multi-Surface Interaction: Supports interaction via one-shot commands, an interactive REPL, a headless daemon, and a Telegram bot, all sharing the same session manager and memory.

Compatibility

Node.js

Runtime

Verified via docs

Anthropic

LLM Provider

Verified via docs

OpenAI

LLM Provider

Verified via docs

Ollama

LLM Provider

Verified via docs

LM Studio

LLM Provider

Verified via docs

Quick start

$ npm install -g agent-afk

Use cases

↳Automating lengthy coding projects: Delegate complex, multi-step coding tasks to run autonomously in the background.

↳Interactive terminal-based development: Use the REPL for real-time coding assistance, tool access, and plan mode, integrating directly into the developer's workflow.

↳Full feature development lifecycle: Orchestrate the entire process from idea (spec) to research, planning, building, verifying, and shipping new features using `/mint`.

↳Automated bug diagnosis and resolution: Employ `/diagnose` to automatically generate and test multiple root-cause hypotheses for failing tests or bugs.

↳Personalized agent knowledge management: Maintain and leverage a persistent memory of preferences, decisions, and procedures across all agent interactions.