Back to browse
Agent Smith – open-source agent that turns issues into pull requests

Agent Smith – open-source agent that turns issues into pull requests

by hleichsenring·Feb 19, 2026·3 points·0 comments

AI Analysis

●●SolidShip ItSolve My Problem
The Take

It actually runs on your infrastructure and exposes the full prompt architecture (17 phases) in the repo — useful for auditing and tuning. It automates the whole loop (clone, plan, implement, test, PR) and supports multiple ticket systems and LLM providers, which is practical for teams who can't use SaaS. That said, the author admits it's best for well-scoped tickets today; large multi-file refactors are still fragile.

Target Audience

Software engineers, repo maintainers, DevOps/platform teams and engineering managers who need private AI-assisted automation

Post Description

Hey HN, I built Agent Smith — a self-hosted AI coding agent that takes a ticket reference, clones your repo, analyzes the code, writes an implementation plan, executes it, and opens a PR. It supports GitHub, Azure DevOps, Jira, and GitLab. You bring your own API key — Claude, OpenAI, or Gemini. No SaaS, no account, runs on your machine or your cluster. I built it in a few days using the same approach the agent itself uses: structured architecture prompts, strict coding principles, and an AI assistant doing the implementation. The coding principles that govern Agent Smith's output are the same ones I used to build it. It's early — works well for well-scoped tickets, not yet reliable for large multi-file refactorings. Interactive chat interfaces (Slack, Teams) are in progress. Would love feedback. The prompts and all 17 architecture phases are in the repo if you want to see how the context is structured.

Similar Projects