Agents
3 months ago I started building a coding agent that runs in the cloud. It's since written every line of code I've shipped, including itself.…
A developer shares their experience building a cloud-based coding agent that has autonomously written all production code shipped over a three-month period, including iteratively improving its own cod
A developer shares their experience building a cloud-based coding agent that has autonomously written all production code shipped over a three-month period, including iteratively improving its own codebase. The project demonstrates a self-referential AI development workflow where the agent handles end-to-end code generation without manual coding from the developer. This represents a practical real-world example of agentic AI systems being used for autonomous software development in production environments.
Related
- I open-sourced an agent architecture that’s born for long-horizon tasks, which Manus and OpenClaw don’t natively support very well
- Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects
- Agent responsibly
- Thank you for helping to make Hermes Agent amazing.
- New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less…
Source: Swyx (X) | 2026-04-13