AI · GitHub repo
AutoGPT
Open-source platform and framework for building autonomous AI agents
Originally created as a viral terminal-based experiment demonstrating autonomous, self-prompting LLM agents, AutoGPT has evolved into a complete agent development platform. It offers both a visual workflow builder and conversational creator to run multi-step automations locally or through a hosted cloud service.
What it's for
- Run autonomous background research on target accounts or web topics
- Automate multi-step business workflows across tools like Gmail, Slack, and GitHub
- Build custom autonomous agents using a drag-and-drop visual canvas or natural language prompts
- Self-host autonomous agent appliances locally via Docker with your own API keys
Features
- AutoPilot natural language conversational builder to generate agents
- Visual drag-and-drop workflow canvas for branching and inspecting agent steps
- Classic standalone autonomous agent runtime preserved under MIT license
- Agent dashboard to monitor run progress, statuses, logs, and token costs
- Integrations with 45+ platforms including Google Workspace, GitHub, Slack, and Notion
- Pre-built community agent marketplace
- Support for hundreds of AI models via API keys or hosted access
Pricing
Freemium. Free to self-host with your own API keys; paid managed cloud platform with usage-based run fees.
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Autonomous Agents
- Open source
- Yes
- Platforms
- Web, Command line, Self-hosted, Linux, macOS, Windows
- For
- Developers and automation builders wanting to create or experiment with autonomous AI agents.
- Alternative to
- BabyAGI, CrewAI, LangChain, Zapier Central
- Tags
- agents, ai, automation, llm, python, open source
Why it was saved
- @wayne_hamadi: Referenced throughout the article as the first AI agent and a formative example of self-prompting agent design.
Compare
Related
Open-source, self-hosted AI agent with persistent memory and messaging integrations.
Open-source, fully local autonomous AI agent that browses and writes code
A Python multi-agent pattern pairing Opus orchestration with Haiku worker instances.
Open-source long-horizon agent harness with Docker sandboxes, memory, and sub-agents
All-in-one AI workspace with autonomous agent tools for content, research, and analysis.
Open vision-to-action foundation model for generalist autonomous game playing
Updated