ADHDev

ADHDev is an open-source agent harness and multi-node orchestration engine developed by Vilmire. Built for complex codebase automation, it provides an execution framework that coordinates autonomous developer agents across multi-package monorepos and Git submodules. Day-to-day operation centers on terminal-driven workflows backed by native terminal emulation (including Ghostty VT integrations) and TypeScript orchestration packages. ADHDev plans and executes tasks using a structured mesh architecture, breaking work into discrete nodes, performing dry-run evaluations, and enforcing execution gates before applying diffs. The harness integrates with frontier LLMs such as Claude to generate code and validate execution paths. ADHDev differentiates itself from standard single-agent CLI tools through its deep Git awareness and multi-node mesh system. It inspects change areas, validates gitlink commits, and executes preflight reachability checks across submodules and remote tracking branches, preventing broken builds and invalid merges before tool execution begins. ADHDev is published as an open-source repository on GitHub with modular packages distributed via npm and native binary platforms.

Tags: agent harness, ai agent, cli, coding agent, developer tools, OpenSource

Visit ADHDev

Key features

  • Mesh orchestration engine — Coordinates multi-node task planning, dry runs, and batch execution pipelines across complex codebases. - Git-aware preflight gates — Validates gitlinks, submodule reachability, and remote tracking refs prior to execution to avoid invalid merges. - Native terminal integration — Incorporates Ghostty VT node bindings for high-performance terminal rendering and process management. - Dry-run planning surfaces — Generates per-node diagnostic verdicts and warning reports before executing code modifications. - Monorepo and submodule targeting — Scopes change areas and dependencies across nested submodules and multi-package workspaces.

Use cases

Use Case: Multi-Submodule Code Refactoring Developers managing monorepos with linked submodules can orchestrate widespread changes while ADHDev verifies gitlink reachability and ensures commits exist on target default branches before completing merges.

Use Case: Preflight Validation for Automated Patches Teams running autonomous coding pipelines can use ADHDev's dry-run planning surfaces to inspect per-node change impacts, catch failure points early, and view batch diagnostic logs without modifying disk state.

Use Case: Monorepo Release and Process Orchestration Engineers orchestrating distributed builds can leverage ADHDev's node execution gates to sequence package builds, manage native artifact pipelines, and automate coordinated multi-package versioning.

Who it is for

ADHDev is aimed at senior software engineers, platform developers, and devops teams managing large TypeScript monorepos or nested Git submodule architectures that require structured multi-agent coordination. It is less suited for developers seeking a simple, single-turn code chat assistant for isolated, single-file scripts.

Install guide

Installation Clone the repository and install dependencies using standard Node/npm package managers: bash git clone https://github.com/vilmire/adhdev.git cd adhdev npm install Build the monorepo packages: bash npm run build

First Run Ensure your target LLM API keys are configured in your shell environment: bash export ANTHROPIC_API_KEY="your-anthropic-api-key" Initialize repository mesh configuration and run the onboarding planner: bash node ./packages/mesh/bin/mesh.js init

Example Session Execute a dry-run plan across repository nodes to inspect changes and submodule reachability before applying modifications: bash node ./packages/mesh/bin/mesh.js refine --plan --dry-run

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories