Authsome is an open-source agent orchestration harness and management platform developed by agentrhq. It provides the runtime tooling and interface needed to configure, execute, and monitor autonomous coding agents and modular agent skills. Authsome operates as a Python-based harness featuring both command-line orchestration tools and a bundled web dashboard interface. It integrates with agent ecosystems via native skill definitions and marketplace extensions (including Claude plugins), allowing developers to inspect agent lists, monitor execution status, and manage multi-step tool calls. Unlike simple single-agent CLI wrappers, Authsome provides an orchestration layer with structured agent detail views, reusable skill modules, and self-hosting infrastructure. This structure allows engineering teams to coordinate and observe agent tasks centrally rather than managing fragmented CLI sessions. Authsome is open-source software hosted on GitHub, packaged via modern Python tooling (uv and Hatchling) for local installation or self-hosted server deployments.
Agent Management Dashboard — Built-in web UI providing agent lists, runtime detail views, and execution inspection. - Claude Plugin Integration — Includes native plugin manifests and skill bindings for Anthropic Claude environments. - Modular Skills System — Structured framework for creating, registering, and running discrete agent skill packages. - Self-Hostable Architecture — Documented configuration for running private on-premise or cloud agent orchestration instances. - Modern Python Distribution — Packaged with Hatchling and uv with pre-bundled UI assets for clean deployments.
Use cases
Use Case: Centralized Agent Monitoring Deploying a self-hosted Authsome instance to track running background coding agents, review detailed task statuses, and audit agent execution logs via the web interface.
Use Case: Claude Environment Extensibility Connecting Authsome's Claude plugin and skill definitions to an Anthropic Claude workflow to expose orchestrator capabilities and custom development tools directly within the model's environment.
Use Case: Standardizing Modular Agent Skills Developing reusable skill packages that can be executed across different automated pipelines and orchestrator instances within a development team.
Who it is for
Authsome is intended for developers and platform teams building, orchestrating, or observing multi-step agent workflows and Claude plugins who require self-hosted management. It is less suited for developers seeking a basic, zero-configuration standalone CLI coding assistant for one-off edits.
Install guide
Installation Install Authsome via Python package managers or directly from source: bash # Standard Python package install pip install authsome # Or install using uv uv pip install authsome To build from source: bash git clone https://github.com/agentrhq/authsome.git cd authsome uv sync
First Run Export your model provider API key and initialize the orchestrator: bash export ANTHROPIC_API_KEY="your-api-key-here" # Launch the Authsome service and UI authsome start
Example Session Inspect connected agents and execute tasks using defined skills: bash # List registered agents authsome agents list # Run a task through an agent skill authsome run --skill ./skills/authsome "Review open pull requests and check for test coverage regressions"
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…