Self-hosted AI agent platform

The central AI
for your team.

One agent per role — with clear boundaries on who sees what, which data, and which tools. Self-hosted, open source, fully audited.

Who can do what Which data Which tools
Open source · AGPL-3.0 · runs fully air-gapped
Pinchy audit trail — signed, tamper-evident event log
Audit chain verified1,284 events · tamper-evident
Open source · AGPL-3.0 GDPR-ready Runs air-gapped
Model-agnostic · works with OpenClaw · Odoo · Gmail · Outlook · Telegram · Ollama · OpenAI · Anthropic

AI features in every tool — but none of them know your team, your data, or your limits.

Pinchy is the one place your team works through AI: across your own software and external tools — with the boundaries set once, at the hub.

One agent per role

Give every team its own assistant

Each agent is scoped to exactly the data and tools its job needs — default-deny, nothing more.

Quote Drafter
Sales

Reads PDF inquiries, suggests prices from your history, and drafts the quote in Odoo. Never sends without a human's approval.

Allowed: odoo.readAllowed: odoo.draftBlocked: send
Support Writer
Customer Ops

Answers from your knowledge base and drafts replies in Gmail or Outlook for a person to review and send, with every source cited.

Allowed: kb.readAllowed: gmail.draftBlocked: gmail.send
Onboarding Guide
People

Walks new hires through setup and answers handbook questions — reading only the directories you've approved.

Allowed: handbook.readBlocked: exec-memos
Invoice Bot
Finance

Matches incoming invoices to purchase orders in Odoo and flags mismatches — read-only on the ledger, no payments.

Allowed: odoo.readBlocked: payments
Boundaries are the product

Safe doesn't have to mean slow.

Boundaries aren't a setting you bolt on — they're a property of the hub. Three questions, answered once, enforced on every action.

Who can do what

Role-based access for people; per-agent permissions for agents. Group visibility controls who even sees which agent.

Which data

Agents read only the directories you grant — read-only, default-deny. The boundary stays at the agent, not flattened into one pool.

Which tools

Agents reach systems through scoped plugins, never raw shell. Every call is gated by the allow-list and written to the signed audit trail.

Pinchy agent permissions — allow-list of tools and directories
Everything included

One platform, fully governed

Self-hosted by design

Your servers.
Your rules.

No US-cloud dependency, no per-seat SaaS, no data leaving your walls. Pair Pinchy with local models and it runs completely offline.

  • GDPR-ready
  • Safe from the US CLOUD Act
  • Air-gap capable
  • Open source (AGPL-3.0)
pinchy — docker compose
$ docker compose up -d

 pinchy-db          started
 pinchy-web         started
 openclaw-runtime   started   (model: ollama/llama3)

 Smithers is ready to help.   http://localhost:3000

Give your team an AI it can trust.

Start a 30-day trial on your own data — or book a 30-minute call and we'll walk through the use case that fits your team.

Open source & built in publicaudit every line on GitHub.

Frequently asked questions.

Is OpenClaw secure enough for enterprise use?

Not on its own. OpenClaw gives agents full system access with no built-in permission layer — that's why Pinchy exists. Pinchy adds Docker container isolation, per-agent allow-list permissions, basic RBAC (Admin / Member roles), group-based agent visibility, and per-row HMAC-SHA256 signed audit trails. Granular RBAC (custom roles, SSO/SAML) is on the roadmap.

How much does it cost to run AI agents?

You control the models, so you control the costs. Docker hosting is free on your own servers. API costs typically run $1 to $150/month per agent depending on model choice and usage volume. Sonnet vs Opus alone is a 10x cost difference.

Can I run this completely offline?

Yes. Pair Pinchy with a local model via Ollama and nothing ever leaves your network. Zero external connections. For teams that need cloud models, just add your API key — your choice.

Do I need to be technical to set this up?

You need to be comfortable with Docker Compose — that's it. Run one command, configure via the admin dashboard. Five minutes from zero to running agents.

Is this really open source?

Yes. Pinchy's core is licensed under AGPL-3.0. Full source code on GitHub. Pinchy's entire codebase is open source. The free Community edition is fully functional for small teams; a paid Pro tier unlocks team-governance features (groups, agent access control, usage analytics) via a license key, not closed code. Inspect it, audit it, deploy it yourself.