Terminal Agent

GITHUB GUIDELINE NOTION-Version 1. The Need for a Fast System in Terminal-Based SWE Data Collection In terminal-based SFT data collection for software engineering (SWE) tasks, system responsiveness is a crucial determinant of both data efficiency and data quality. For annotators who are not proficient with command-line interfaces, two fundamental issues—slow typing speed and difficulty recalling commands—create significant friction in the labeling process. First, the interaction cost of terminal input is inherently high. Unlike graphical interfaces that offer affordances such as buttons, menus, or auto-completion, terminals rely entirely on textual command entry. Each operation requires the annotator to recall and retype precise commands and parameters, often under the risk of syntax errors. When annotators frequently make syntax or command errors due to limited terminal proficiency, the repeated cycles of editing, rerunning, and verifying become time-consuming and mentally exhausting, causing substantial inefficiency and fatigue throughout the labeling process. ...

GITHUB DOC Introduction We propose Reptile, a terminal agent that operates under an extended REPL (Read-Execute-Print-Learn Loop) protocol, where human feedback is seamlessly integrated into the agent’s execution loop. Unlike traditional REPL (Read-Execute-Print Loop) environments that focus solely on code evaluation, our REPL protocol emphasizes the iterative cycle of human-agent collaboration, transforming the terminal from a passive command executor into an interactive learning environment. What Makes Reptile Special? Compared with other CLI agents (e.g., Claude Code and Mini SWE-Agent), Reptile stands out for the following reasons: ...

GITHUB TWITTER NOTION-Version LLM systems today are gravitating toward structured “tool protocols”. The most prominent of these, MCP, defines tools through JSON schemas that describe how models can interact with a computer. But here’s the quiet irony: models already know. They’ve seen countless examples of people running commands, inspecting logs, and fixing errors — all through a single interface that’s existed for half a century: the terminal. The burden of new protocols Modern tool frameworks like MCP describe every action in meticulous JSON. They are explicit, structured and heavy. To use them, an endless catalog of tool descriptions need to be maintained and explained in the system prompt. ...