by LobsterQBA · Agent Tool · ★ 44
Loop Agent A small Python app that shows how an agent uses tools to finish a task. Ask it to calculate 17 × 23 and save the result. It runs the calculator, stores in SQLite, and shows each tool call and result. Restart the app and ask for the value again: it is still there. I built this to understand the loop behind a tool-using agent: choose an action, run it, read the result, and decide what to do next. The core loop is in agent.py. Try the browser demo → The browser demo replays three recorded runs: calculate and save, recall after a restart, and handle a failed calculation.
| Stars | 44 |
| Forks | 5 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.377650656029/100 |
| Last Updated | 2026-10-01 |
| Created | 2026-08-07 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with loop-agent for enhanced workflows:
Explore other popular agent tool tools:
loop-agent is A Python app that shows how an agent calls tools, saves results, and recalls them after a restart.. It is categorized as a Agent Tool with 44 GitHub stars.
loop-agent is primarily written in Python. It covers topics such as agent-observability, ai-agents, human-in-the-loop.
You can find installation instructions and usage details in the loop-agent GitHub repository at github.com/LobsterQBA/loop-agent. The project has 44 stars and 5 forks, indicating an active community.
loop-agent is released under the MIT license, making it free to use and modify according to the license terms.