Nodal-Agents
A local-first, self-hostable multi-agent AI platform with a web dashboard — install in one command.
Build a team of AI agents that run entirely on your machine. Any model, persistent memory, your own tools — installed with one command. No cloud account, no lock-in.
🚀 Get started
Install and run your first agent in two minutes.
🧩 Core concepts
Agents, orchestrators, skills, memory, the learning loop.
📦 Self-hosting
Ports, data, auth modes, updates.
🛠️ Skills reference
Every capability you can assign — generated from the catalog.
Install
npm install -g nodal-agents
nodal-agents upOpens the dashboard on localhost:3000 with an embedded Postgres — no external database, no Redis, no config files to edit. Or npx nodal-agents up, with nothing installed globally.
If npm prints npm warn allow-scripts, approve @embedded-postgres/<platform> and install again. It prepares the database binaries. How.
Requires Node 22+. Everything — conversations, memory, credentials — stays in ~/.nodalai/ on
your machine.
What you get
- Local-first — single command, embedded Postgres; your data never leaves your machine.
- Any model, per agent — Anthropic, OpenAI, Google, native DeepSeek & MiniMax, OpenRouter, or local (LM Studio / Ollama). One key per provider; each agent picks its own model.
- Orchestrators that finish — route to one specialist and resume on its result, or fan out independent work to many sub-agents in parallel and compile the answer.
- Memory that compounds — persistent facts auto-injected into every job, plus chat continuity across sessions.
- Self-improving agents — an opt-in learning loop: after a substantial job an agent reflects and writes itself a reusable skill; a curator consolidates them.
- Skills, connectors & MCP — assign reusable skills, connect Gmail / Drive / Notion, and add MCP servers over HTTP and stdio.
- Proof, not claims — a run's file list is read back from git, the agent declares the commands that check its own work, and every write is preceded by a snapshot you can restore from the CLI.