KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant

TL;DR

KISS Sorcar is a simple, open-source AI assistant integrated into VS Code, designed to improve software engineering tasks through a robust multi-layered agent framework that emphasizes output quality and long-horizon task management.

Contribution

It introduces the KISS Agent Framework, a minimalistic yet effective multi-layered agent system, and demonstrates its application in a practical IDE extension for enhanced software engineering.

Findings

Achieves 62.2% pass rate on Terminal Bench 2.0 with Claude Opus 4.6.

Effectively supports long-horizon tasks, browser automation, multimodal input, and Docker.

Prioritizing thorough validation reduces low-quality code issues.

Abstract

Large language models can generate code and call tools with remarkable fluency, yet deploying them as practical software engineering assistants still expose stubborn gaps: finite context windows, single mistakes that derail entire sessions, agents that get stuck in dead ends, AI slop, and generated changes that are difficult to review or revert. We present KISS Sorcar, a general-purpose assistant and integrated development environment (IDE) built on top of the KISS Agent Framework, a stupidly-simple AI agent framework of roughly 1,850 lines of code. The framework addresses these gaps using a robust system prompt and through a five-layer agent hierarchy in which each layer adds exactly one concern: budget-tracked ReAct execution, automatic continuation across sub-sessions via summarization, coding, and browser tools with parallel sub-agents, persistent multi-turn chat with history recall, and git worktree isolation so every task runs on its own branch. To assess the power of the KISS agent framework, we implemented KISS Sorcar as a free, open-source Visual Studio Code extension that runs locally and effectively for long-horizon tasks, and supports browser automation, multimodal input, and Docker containers. In this research, we deliberately prioritize output quality over latency: giving a frontier model adequate time to validate its own output -- running linters, type checkers, and tests -- dramatically reduces the low-quality code that plagues faster but less thorough agents. The entire system was built using itself in 4.5 months, providing a continuous stress test in which any agent-introduced bug immediately impairs its own ability to work. On Terminal Bench 2.0, KISS Sorcar achieves a 62.2% overall pass rate with Claude Opus 4.6, comparing favorably to Claude Code (58%) and Cursor Composer 2 (61.7).