Back to browse
I built a tool I needed

I built a tool I needed

by akad·Feb 23, 2026·1 point·0 comments

AI Analysis

●●SolidShip ItSolve My Problem

Paragent stays in-editor, but Cursor, Aider, and GitHub Copilot already do this better.

Strengths
  • Parallel agent execution with automatic branch isolation eliminates merge conflicts
  • Costs tied to your own API keys (OpenAI, Anthropic, Gemini) for full transparency
  • Sidebar PR management and job retry/cancel commands keep workflow inside editor
Weaknesses
  • AI code generation in editors is a crowded category with larger, better-funded competitors
  • No visible differentiation on code quality, speed, or accuracy vs. existing solutions
Target Audience

Software developers using VS Code or Cursor who want AI-assisted code generation in their editor

Similar To

GitHub Copilot · Cursor · Aider

Post Description

> I kept doing the same thing: open the browser, go to the Paragent dashboard, describe a feature, wait for the agent, then switch back to VS Code to keep coding. It worked, but the context switching was annoying. > > I wanted to stay in the editor. Describe the feature, hit run, and keep working while the agent runs in the background. When it's done, open the PR from the sidebar. No tabs, no dashboard. > > So I built a VS Code extension for it. You describe what you want, pick a repo and model, and it creates a branch, writes the code, and opens a PR. You can run several agents at once, each on its own branch. It uses your own API keys (OpenAI, Anthropic, Gemini), so you control the cost. > > I've been using it for a few weeks and it's changed how I work. I'm shipping it on the VS Code Marketplace today. It also works in Cursor. > > Happy to answer questions or hear how you'd improve it.

Similar Projects

Developer Tools●●Solid

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

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.

Ship ItSolve My Problem
hleichsenring
303mo ago