PluginWorld
Cl

clawdi

Claude Code✓ SPEC VERIFIED

The best home for all your AI agents. Run them in the cloud or connect your own—with their context and tools in one place.

@Clawdi-AI · v0.14.100 · MIT · updated 12d ago

SECURITY

A

SCORE

81

INSTALLS

▲ 15.3K

PLUG IN

/plugin marketplace add Clawdi-AI/clawdi
/plugin install clawdi

README

Clawdi

The best home for all your AI agents.
Run them in the cloud or connect your own—with their context and tools in one place.

npm version CI status GitHub stars MIT License

Website · Docs · Product tour · npm

Clawdi overview with two running demo Agents and a 12-month activity history

Clawdi supports two run paths:

  • Cloud Agents: managed Hermes or OpenClaw runtimes.
  • Connected Agents: supported Agent software running on your computer.

Features vary by Agent software and run path.

Start

Deploy a Cloud Agent, or connect an Agent on macOS or Linux:

curl -fsSL https://clawdi.ai/install.sh | sh
clawdi auth login
clawdi setup
clawdi doctor

Windows and package-manager installs require Node.js 24+:

npm i -g clawdi

See the Connected Agent quickstart.

Capabilities

  • Context: Sessions and durable Memories.
  • Resources: Projects, Skills, and Vaults.
  • Integrations: MCP Connectors and messaging Channels.
  • AI Providers: model access for supported local and Cloud Agent runtimes.
  • Open source: MIT-licensed CLI, FastAPI backend, TanStack dashboard, and PostgreSQL.

See Core concepts for support and access boundaries.

Connected Agent support

Agent Sessions Skills MCP setup
Claude Code Yes Yes Automatic
Codex Yes Yes Automatic
Hermes Yes Yes Automatic
OpenClaw Yes Yes Manual hint where required
Pi Yes No No
OpenCode Yes No No

Self-host

git clone https://github.com/Clawdi-AI/clawdi.git
cd clawdi
bun install
apps/web/          TanStack dashboard
backend/           FastAPI backend and migrations
packages/cli/      CLI, Agent adapters, and MCP server
packages/shared/   Shared API types and schemas
docs/              Architecture and contributor guides

Follow AGENTS.md#local-end-to-end. Technical references: Architecture, AI Providers, and Managed runtime.

Development

bun run typecheck
bun run test
bun run check

See AGENTS.md for repository workflows.

License

MIT. See LICENSE.

SIMILAR PLUGINS