StarShell: Terminal Agents Suffice for Enterprise Automation

Abstract

There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Yet, it remains unclear whether such complex agentic systems are necessary given their cost and operational overhead.

We argue that a coding agent equipped only with a terminal and a filesystem can solve many enterprise tasks more effectively by interacting directly with platform APIs. We evaluate this hypothesis across diverse real-world systems and show that these low-level terminal agents match or outperform more complex agent architectures. Our findings suggest that simple programmatic interfaces, combined with strong foundation models, are sufficient for practical enterprise automation.

Overview

Overview of StarShell: a minimal terminal agent for enterprise automation. The agent operates through a terminal and filesystem, optionally using documentation and persistent skills to discover and invoke APIs directly on enterprise platforms (e.g., GitLab, ServiceNow, ERPNext), without relying on GUI interaction or pre-defined tool registries.

Results

We evaluate three agent architectures — Terminal (bash), MCP (tool-augmented), and Web (Playwright) — across three enterprise platforms and multiple foundation models. SR is the success rate (%) and Cost is the average cost per task in USD.

Agent	ServiceNow		GitLab		ERPNext		Overall
Agent	SR	Cost	SR	Cost	SR	Cost	SR	Cost
Claude Sonnet 4.6
MCP	11.5	0.76	45.2	0.48	55.6	0.14	32.9	0.51
Web	72.4	4.49	82.9	0.88	61.8	3.63	72.2	3.29
Terminal	73.6	0.78	76.5	0.28	67.6	0.46	72.7	0.56
Claude Opus 4.6
MCP	16.1	0.66	46.8	0.90	68.9	0.17	39.2	0.58
Web	77.6	4.21	81.9	0.85	81.6	6.49	79.9	3.97
Terminal	79.1	1.94	80.2	0.50	76.8	0.72	78.7	1.22
GPT-5.4 Thinking (Medium)
MCP	18.5	0.14	47.9	0.40	62.8	0.21	38.8	0.23
Web	69.4	0.54	81.4	0.17	72.5	0.51	73.4	0.43
Terminal	77.0	0.20	71.3	0.13	70.0	0.24	73.5	0.19
Gemini 3.1 Pro
MCP	14.2	0.10	48.9	0.15	62.8	0.07	37.1	0.11
Web	62.1	0.68	84.6	0.22	65.2	1.13	68.9	0.69
Terminal	78.5	0.10	79.8	0.06	73.9	0.10	77.5	0.09

Terminal agents consistently match or outperform MCP and Web agents while being significantly cheaper. Bold indicates best or tied-best per model–platform.

Skills Accumulation

The terminal agent can persist reusable procedures (skills) across sequential tasks. Top: cumulative number of successful tasks. Middle: cumulative cost ($USD). Bottom: skills directory size (KB). The agent with memory (blue) accumulates reusable procedures; the baseline (black) starts fresh every time.

BibTeX

@article{bechard2026terminal,
  title   = {Terminal Agents Suffice for Enterprise Automation},
  author  = {Bechard, Patrice and Ayala, Orlando Marquez and Chen, Emily and Skelton, Jordan and Davasam, Sagar and Sunkara, Srinivas and Yadav, Vikas and Rajeswar, Sai},
  journal = {arXiv preprint arXiv:2604.00073},
  year    = {2026}
}