GitHub - agentrhq/authsome: Credential vault for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

Credential broker and vault for AI Agents

An open-source credential broker that sits between your agents and the services they call. Instead of sharing credentials with every agent, log in once via OAuth2 or API keys. Authsome stores credentials securely and injects them via an HTTP proxy. You get one place to manage access, rotate keys, and see what every agent is doing.

Bundled providers out of the box — OAuth2 and API key. See the full list.

Demo

demo.mp4

Why Agents Need Authsome

Agents run beyond interactive sessions. They live in CI, over SSH, in cron jobs, in background workers, and in parallel pipelines. They need API access that survives without a human in the loop.

Hardcoded environment tokens leak or go stale, and building auth flow logic, token storage, refresh handling, and per-provider config into every project rebuilds the same plumbing every time.

Authsome is the local credential layer agents call at runtime.

No credential sprawl. One encrypted store. Every provider, every agent, one place.
Agents never see credentials. Auth is handled outside the agent process — no exfiltration risk, no secrets in environment variables.
No browser required at runtime. Setup can use browser PKCE, device code, or a browser bridge for secure API key entry. After that, agents run headlessly.

How It Works

The CLI is the agent's interface: setup once, then inject fresh credentials whenever a tool runs.

Authenticate once:

authsome login github
# This opens a browser on user's machine
# user completes login without sharing the creds with the agent.

Then agents get valid credentials on demand when they try to access external services. All they need to do is use authsome run -- before the command they want to run:

authsome run -- curl -s "https://api.github.com/user/repos?per_page=10"
# runs behind a local auth proxy that injects headers at request time
# without exposing secrets in the child process environment.
# matched automatically via provider api_url (e.g. api.openai.com)

Credentials are encrypted at rest and refreshed before expiry.

Why Authsome

	authsome	Hardcoded env tokens	DIY
Automatic token refresh	✅	❌	build it
OAuth2 + API keys	✅	❌	build it
Runtime headless use	✅	✅	varies
Built-in providers, zero config	✅	❌	❌
Multi-account per provider	✅	❌	build it
Agents never see credentials	✅	❌	build it

Authsome gives agents one command for a valid token, without scattering long-lived secrets across every project.

Install

Requires Python 3.13+.

Self-hosting

Run a persistent daemon in Docker — no Python required on the host:

docker compose up -d
export AUTHSOME_DAEMON_URL=http://localhost:7998

See the self-hosting guide for volume backup, TLS termination, and environment variable reference.

Quick Start

Add the authsome skill to your agent (claude, codex, cursor, hermes, etc.):

npx skills add agentrhq/authsome

And try a sample task that requires access to external services:

Star the repo agentrhq/authsome

Get my last 5 emails from gmail

The agent will use authsome to login into external services and perform the task.

Agent Integrations

Authsome ships with adapters for the most common agent frameworks and CLIs:

Full list at authsome.ai/docs/integrations.

Community

Discord for questions, help, and showing what you're building.
GitHub Issues for bugs and feature requests.

Roadmap

See authsome.ai/docs/roadmap for what's shipped, what's next, and what's out of scope.

Contributing

Found a bug? Open an issue
Have an idea? Start a discussion
Want to contribute? Read CONTRIBUTING.md for development setup, testing, and the engineering principles we follow.

Star History

License

MIT. See LICENSE.