Hermes Agent is an open-source terminal-based AI coding agent developed by NousResearch. Designed to bridge terminal workflows and modern IDE environments, it provides interactive execution, automated tool orchestration, and deep repository interaction powered by open-weight and proprietary language models.
Agent Client Protocol (ACP) Adapter — Integrates directly with supported editor surfaces and desktop client protocols for bidirectional agent-editor communication. - Interactive TUI and CLI Modes — Provides terminal user interfaces built on prompt_toolkit alongside standard non-interactive command-line execution modes. - Protected Dangerous Action Approval Gate — Enforces explicit user confirmation boundaries on file modifications, command executions, and configuration changes. - Secure Browser Automation & Profiling — Supports browser integration with dedicated credential snapshot handling, channel verification, and profile isolation. - Configurable File Safety Subsystem — Includes strict denylists and access controls to prevent reading or archiving sensitive files, auth tokens, and session databases.
Use cases
Use Case: Interactive Terminal Development Developers run Hermes Agent directly inside their terminal to inspect codebases, execute terminal commands, and apply iterative code modifications under an explicit approval harness.
Use Case: Editor Integration via ACP Teams connect Hermes Agent to their preferred IDE or editor interfaces via the Agent Client Protocol (ACP) adapter, synchronizing file changes, approvals, and agent runs across workflows.
Use Case: Browser-Augmented Task Automation Engineers leverage the agent's built-in browser profile tooling to automate web interactions, test end-to-end user flows, and capture authenticated session states safely.
Who it is for
Hermes Agent is built for developers, AI researchers, and teams looking for an open-source, extensible CLI and ACP-compatible coding harness that prioritizes safety permissions and local execution control. It is less suited for developers seeking a closed-source, zero-configuration proprietary IDE plugin with turn-key cloud subscription billing.
Install guide
Installation Clone the repository and install the package using Python: bash git clone https://github.com/NousResearch/hermes-agent.git cd hermes-agent pip install -e .
First Run Configure your model provider credentials and environment variables before launching: bash export OPENAI_API_KEY="your-api-key" # or set up your local model endpoint hermes
Example Session Start an interactive session to inspect and refactor code in your working repository: bash hermes "Audit the src/ directory for unhandled exceptions and draft tests for missing edge cases"
nanoclaw — nanoclaw is an open-source CLI agent framework and containerized execution harness developed by Nanoco AI. Designed around Claude-powered workflows and…
Nullclaw — Nullclaw is an open-source, lightweight AI coding assistant and agent harness designed to operate with minimal overhead. Developed using Zig…
Orkas — Orkas is an open-source desktop agent harness and workflow orchestrator developed by Orkas-AI. Built to bridge autonomous AI execution 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.…
Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…