LoopTroop is an open-source AI coding agent harness and orchestration framework maintained by the looptroop-ai organization on GitHub. Built with TypeScript, it is designed to manage autonomous coding loops, plugin execution, and multi-step agent workflows across local development environments. In daily operations, LoopTroop runs in terminal environments to orchestrate task execution cycles. It integrates with development toolchains, execution plugins (such as OpenCode plugins), and underlying LLM APIs to plan tasks, invoke shell commands, inspect diffs, and iterate on code changes until automated checks or tests pass. Unlike monolithic CLI coding assistants, LoopTroop functions primarily as an orchestration harness. It focuses on modular plugin extensions, continuous feedback loops via testing suites (such as Vitest), and multi-platform distribution across standard package managers, including Windows Scoop and npm. LoopTroop is distributed as open-source software on GitHub. It operates on a bring-your-own-key model for model inference providers, incurring no software licensing fees.
Agentic Loop Orchestration — Automates iterative execution cycles of coding, testing, and error recovery in local repositories. - Plugin Architecture — Supports modular integration via plugin architectures such as OpenCode plugins for extending agent capabilities. - Test-Driven Feedback Loops — Natively incorporates automated test suites (e.g., Vitest) to validate generated diffs before task completion. - Cross-Platform Support — Includes packaging and CI support across operating systems, including Windows (via Scoop) and Unix environments. - TypeScript Ecosystem — Built natively on Node.js/TypeScript for maintainability and direct integration into modern JavaScript development pipelines.
Use cases
Use Case: Automated Test-Driven Bug Fixing A developer assigns a failing test case to LoopTroop. The harness executes the test suite, parses failure output, applies targeted edits across codebase files, and re-executes tests in a loop until all assertions pass.
Use Case: Dependency Upgrades and Refactoring When bumping dependency versions across a project, LoopTroop orchestrates the package update, monitors build outputs and typechecker warnings, and iteratively fixes breaking changes introduced by API modifications.
Use Case: OpenCode Plugin Execution Teams using OpenCode ecosystem tools utilize LoopTroop as an execution runner to invoke specialized plugins for linting, security scanning, and workspace automation within an orchestrated agent session.
Who it is for
LoopTroop is aimed at software engineers and agent workflow developers who require an extensible, loop-based orchestrator for terminal and CI coding agents. It is less suitable for non-technical users seeking a simple GUI assistant or developers looking for a basic inline code autocomplete plugin.
Install guide
Installation Install LoopTroop globally via npm or your system package manager: bash npm install -g looptroop On Windows via Scoop (if published to a tracked bucket): powershell scoop install looptroop
First Run Set your target LLM provider API key in your environment before initializing a session: bash export ANTHROPIC_API_KEY="your-api-key" # Or configure OpenAI API access export OPENAI_API_KEY="your-api-key" Initialize LoopTroop inside your project repository: bash looptroop init
Example Session Run an orchestrated task loop against your current project: bash looptroop run "Refactor database connection pool and ensure all vitest suites pass"
AgentPack — AgentPack is an open-source orchestration harness and configuration management framework developed by Vishal (vishal2612200) for multi-agent coding environments. It standardizes…
Crystal — Crystal is an open-source AI coding harness and desktop-oriented agent platform maintained by Stravu. Designed as an Electron-based application with…
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Continue — Continue is an open-source AI code assistant and agent framework originally developed by the Continue team (continuedev) and recently acquired…
Vibe Kanban — Vibe Kanban, originally developed by Bloop AI, is an open-source orchestration harness and visual task board designed to manage and…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…