TeDDy (developed by atte500) is an open-source test-driven execution harness and orchestrator written in Python. It is designed to manage coding agent lifecycles, test execution passes, and debugging loops directly against a local codebase. Operating primarily as a terminal-based execution framework via `teddy_executor`, TeDDy manages runtime test runners, tee I/O capture handlers, and diagnostic output streaming. The orchestrator coordinates validation runs, handles timeout and error recovery stages, and extracts structured execution metrics from development runs. Unlike standalone conversational CLI agents, TeDDy functions as an underlying orchestration harness emphasizing test-driven validation, artifact-based probe mechanisms, and cross-platform pre-commit lifecycle hooks. It provides the execution scaffolding necessary to run, test, and debug agentic code changes systematically. TeDDy is an open-source project hosted on GitHub and is available under standard open-source development workflows.
Tags: cli, codebase, developer tools, experiments, OpenSource