Open Source · Local-First · Apache 2.0

Stop copying API keys
into every tool.

AgentKeyring manages your LLM provider keys in one place and syncs them into the AI agents and clients on your machine.

AgentKeyring
$ agentkeyring add --provider openai
✓ API key saved for OpenAI
✓ Key validated — 3 models available
$ agentkeyring scan
Found 4 AI tools on this machine:
• Cursor editor
• Claude Code cli
• Cline extension
• aider cli
$ agentkeyring sync --all
✓ Synced OpenAI key → Cursor
✓ Synced Anthropic key → Claude Code
✓ Synced OpenAI key → Cline
✓ Synced OpenAI key → aider
All tools configured. Backups saved.

The problem

Using AI tools locally means repeating the same tedious setup.

🔑

Copying API keys into different tools one by one

📁

Figuring out where each tool keeps its config files

🔄

Switching between providers and models manually

📝

Editing env vars, JSON, and YAML by hand

🐛

Debugging why a tool still doesn't work

⏱️

Repeating this every time you try a new tool

What AgentKeyring does

One tool to manage keys, validate them, and push config where it needs to go.

Centralized Key Management

Store API keys for OpenAI, Anthropic, and other providers in one secure local vault.

Key Validation

Instantly verify whether a key is valid and working before you use it anywhere.

Model Discovery

See which models are available for each provider and key — no guessing required.

Tool Detection

Automatically discover AI agents and clients installed on your machine.

Config Sync

Push the right keys into the right tools with connector-based configuration sync.

Safe by Default

Backups are created before any config write. You always know what changed.

How it works

Three steps. No cloud. Everything stays on your machine.

1

Add your keys

Enter API keys for any supported LLM provider. Keys are stored locally and validated on the spot.

2

Scan your tools

AgentKeyring detects AI agents, editors, and CLI tools installed on your system.

3

Sync config

Push the right keys into the right config files. Backups are created automatically.

Early target integrations

Starting with the tools developers use most. More coming soon.

LLM Providers

OpenAI Anthropic Google Gemini Mistral DeepSeek + more

Agent CLI Tools

Claude Code aider Open Interpreter + more

Coding Assistants

Cursor Cline Continue Copilot + more

Config Targets

.env files JSON config YAML config Shell exports

What AgentKeyring is not

A chat client

A hosted LLM platform

A proxy gateway

A replacement for your existing AI tools

It is a local-first configuration and credential management tool.

FAQ

Is AgentKeyring free?

Yes. AgentKeyring is open source under the Apache License 2.0. Free to use, modify, and distribute.

Does it send my keys to a server?

No. AgentKeyring is local-first. Your keys never leave your machine. Validation calls go directly from your machine to the provider's API.

What platforms are supported?

The MVP targets macOS and Linux first. Windows support is planned.

Can I add my own integrations?

Yes. The connector-based architecture is designed to be extensible. Community connectors are welcome.

What happens if a sync goes wrong?

AgentKeyring creates a backup of every config file before writing. You can always roll back.

Ready to simplify your LLM setup?

AgentKeyring is in early development. Star the repo, open an issue, or join the discussion.