A Python framework and runtime for building, serving, and managing AI agent platforms, with a web UI for administration.
fetchai/uAgents
A Python framework for building autonomous AI agents that run on schedules or react to events, with agents able to join the Fetch.ai network.
- Stars
- 1,643
- Forks
- 358
- Open issues
- 64
- Last commit
- 18 hours ago
What is it?
uAgents is a Python library from Fetch.ai for creating autonomous agents. Developers define agent behavior with decorators, such as running a task on a fixed interval or responding to incoming messages, and can start an agent with a few lines of code.
Each agent gets an address and can register itself on the Almanac, a smart contract on the Fetch.ai blockchain, so other agents on the uAgents network can find and message it. Messages and wallets are cryptographically signed, and agents registered on Agentverse can send start/stop, message and error events to its dashboard.
The repository includes the Python library and a uagents-core package with the core definitions for building agents that integrate with the Fetch.ai ecosystem. Installation is via pip for Python 3.10 to 3.13.
Key features
- 01Create agents in Python using simple decorators for scheduled and event-driven tasks.
- 02Agents register on the Almanac smart contract to be discoverable on the uAgents network.
- 03Messages and wallets are cryptographically secured.
- 04Optional event telemetry reporting to the Agentverse dashboard.
Use cases
- Building scheduled background agents that run tasks at fixed intervals.
- Creating agents that communicate with other agents on the Fetch.ai network.
- Prototyping LLM-powered agents that respond to incoming messages.
Quick start
- 1
Install uagents from PyPI (Python 3.10 to 3.13)
pip install uagents - 2
Create a file with the agent script shown in the README
- 3
Run the agent script
python agent.py
Things to know
- The README's disclaimer provides the software as-is, without warranty or liability.
- Agents joining the network register on the Almanac smart contract on the Fetch.ai blockchain.
Topics
FAQ
- What is uAgents?
- A Python framework for building autonomous AI agents that run on schedules or react to events, with agents able to join the Fetch.ai network. uAgents is a Python library from Fetch.ai for creating autonomous agents. Developers define agent behavior with decorators, such as running a task on a fixed interval or responding to incoming messages, and can start an agent with a few lines of code.
- Is uAgents free to use? What license does it have?
- uAgents is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is uAgents still maintained?
- Actively maintained. The last commit to uAgents was on Oct 20, 2026.
- What can I use uAgents for?
- Building scheduled background agents that run tasks at fixed intervals. Creating agents that communicate with other agents on the Fetch.ai network. Prototyping LLM-powered agents that respond to incoming messages.
- How do I install uAgents?
- Install uagents from PyPI (Python 3.10 to 3.13): pip install uagents Create a file with the agent script shown in the README Run the agent script: python agent.py
- Where can I get uAgents?
- The source code and installation instructions are on GitHub: https://github.com/fetchai/uAgents
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source SDK for building and running AI agents in Python and TypeScript, with tools, MCP, memory, and model portability.
AutoGPT is an open-source platform for building, running, and scheduling AI agents that carry out multi-step workflows from plain-English descriptions or a visual builder.
A Python framework for building LLM-powered applications and agents, with standard interfaces for models, embeddings, vector stores and third-party integrations.
Open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven workflows (Flows).
A low-level Python framework for building stateful, long-running agents with durable execution, human-in-the-loop and memory.