Herdr

Herdr is an open-source agent harness and orchestrator designed to coordinate, manage, and execute autonomous terminal-based AI coding workflows. Developed under the herdrdev organization, the tool acts as a control plane for AI agents, organizing tasks across isolated workspace groups and repositories. In daily operations, Herdr manages agent lifecycles, scoped skill sets, and working trees directly from the command line. It delegates coding tasks to underlying agents and tools while enforcing boundary isolation across project workspaces. The platform incorporates terminal emulation capabilities—including native ConPTY support on Windows—to reliably run interactive terminal sessions, agent tooling, and environment scripts. Herdr differentiates itself by treating workspace management, skill definition, and agent orchestration as first-class infrastructure rather than simple process wrappers. By decoupling agent execution from the primary working directory via worktree and workspace group isolation, it prevents unintended side effects across development branches. Herdr is maintained as an open-source project on GitHub with build and packaging configurations for multiple environments, including Nix and Windows.

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

Visit Herdr

Key features

  • Workspace Group Isolation — Manages isolated working trees and workspace groups to safely isolate multi-agent operations from active working directories. - Agent Skills Architecture — Supports modular, scoped agent skill definitions stored and versioned within .agents/skills. - Cross-Platform Terminal Emulation — Provides cross-platform terminal runtime handling, including modern ConPTY bundling for Windows environments. - Reproducible Environment Support — Integrates Nix configurations for reproducible developer environments and deterministic dependency management. - Editor and Tooling Integrations — Compatible with modern developer environments, terminal workflows, and language servers including Zed.

Use cases

Use Case: Multi-Agent Parallel Refactoring Developers coordinate multi-step refactoring efforts across isolated Git worktrees without risking corruption to their current working tree. Herdr coordinates individual agent runs against separate branches and ensures explicit workspace boundaries are maintained.

Use Case: Version-Controlled Agent Skill Deployment Teams maintain standardized operational skills in .agents/skills that agents can execute during automated tasks. Herdr scopes and invokes these skills during task execution to standardize linting, testing, and release prep procedures.

Use Case: Deterministic Multi-Platform Agent Execution Engineers operating across Linux, macOS, and Windows run identical agent orchestration pipelines. Herdr handles terminal capture and ConPTY mechanics to ensure consistent terminal execution across operating systems.

Who it is for

Herdr is built for software engineers and development teams who run terminal-based coding agents across complex codebases and need robust workspace isolation and skill orchestration. It is not intended for users looking for lightweight single-file chat interfaces or basic autocomplete IDE plugins.

Install guide

Installation Clone the repository and build via Nix or Cargo (standard toolchain installation): bash # Clone the repository git clone https://github.com/herdrdev/herdr.git cd herdr # Build and run using Nix flakes (if Nix is installed) nix build # Or build from source with standard Rust toolchain cargo build --release

First Run Initialize the project configuration and inspect available agent skills: bash # Initialize workspace configuration in your project root herdr init # Check agent skill registrations herdr skills list

Example Session Launch an orchestrated agent task in an isolated workspace group: bash # Execute a task across a managed workspace group herdr run --workspace feature-refactor "Migrate internal auth handlers to new interface"

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