Pinchy vs amber
amber (amberSearch) is a managed, German-hosted enterprise AI assistant — permission-aware search and a "company GPT" across your knowledge silos, operated by amber in its German cloud. Pinchy is open source (AGPL) and self-hosted: you run it, with per-agent permissions and a signed audit trail. Both take GDPR seriously — they just put your data in very different places.
The Core Difference
A polished, German-hosted assistant that indexes your knowledge silos and answers permission-aware, with source citations. amber operates it in its own German cloud. The centre of gravity is company-wide knowledge search at scale.
Run a single Docker stack on your own servers, with your own models. The centre of gravity is governed action: which tools each agent may use, a signed record of every call, and the option to run fully air-gapped.
amber is closed-source and operated by amber, with your data in its cloud. Pinchy is AGPL-3.0: you can read the code, change it, patch it on your schedule, and run it on infrastructure no vendor can reach.
Side by Side
Figures as of June 2026, from each vendor's public pricing and product pages. Check each vendor for current details.
| Pinchy | amber | |
|---|---|---|
| Category | Self-hosted agent platform | Managed AI search & company-GPT |
| License | AGPL-3.0 (open source) | Proprietary (closed source) |
| Who operates it | You (Docker, your servers) | amber (Open Telekom Cloud, Germany) |
| Self-host / on-prem | Yes — the default, any size | Enterprise tier only (500-seat min) |
| Where your data lives | Your infrastructure | amber's German data centres |
| Fully offline / air-gapped | Yes (local model via Ollama) | No (managed cloud) |
| Free tier | Yes (AGPL, free forever) | 30-day free trial (no card) |
| Pricing | Free + flat Pro (not per seat) | Public per seat: €9.99–17.99/user/mo (50-user min on paid tiers) |
| Enterprise search across silos | Focused connectors | Core strength (50+ connectors: SharePoint, M365, Confluence, Slack) |
| Per-agent tool permissions | Allow-list per agent (default-deny) | Permission-aware retrieval (inherited ACLs) |
| Agent actions (write / automate) | Native, sandboxed, per-agent allow-list | Delegated to n8n / Make / Zapier |
| Audit of agent actions | HMAC-signed per row, CSV export | Source citations & usage stats |
| ERP-native (Odoo) | Deep, first-class (read + write) | Via generic connectors |
| Channels | Web UI + per-agent Telegram bots | Web, Teams, mobile, desktop |
| Data residency / compliance | GDPR by architecture (your servers) | GDPR + EU AI Act, ISO 27001, hosted in Germany |
Being Honest
amber's core is permission-aware search across SharePoint, Confluence and Microsoft 365 at scale, with source attribution and multilingual results. For company-wide "find and ask across everything," it's purpose-built — and proven across 200+ deployments.
amber runs it for you, deployed in hours without data migration. If you don't want to operate infrastructure and want results fast, a managed service is a real advantage over self-hosting.
German data centres, ISO 27001, GDPR and EU AI Act alignment, "Made in Germany." For organisations that want a managed EU-cloud assurance rather than running their own stack, that's a simple, strong story.
Multilingual queries, deep research, web-search augmentation, image generation, and native Teams, mobile and desktop apps. A broad assistant the moment it's switched on.
Where Pinchy Wins
Pinchy is AGPL-3.0. Read the code, modify it, fork it, patch on your own schedule. With amber you depend on a proprietary vendor — and your data sits in their cloud.
One Docker Compose stack on your own servers, your own models. Paired with Ollama, nothing leaves your network — air-gapped if you need it. That's data sovereignty beyond a "German cloud" promise: the data simply never leaves.
Pinchy is free under AGPL with a flat Pro tier — not a per-seat subscription with a floor. amber's paid tiers start at a 50-seat minimum; with Pinchy a three-person team and a fifty-person team can both start today.
Every agent starts with zero tools; admins enable each one explicitly. Every tool call is recorded in an individually HMAC-signed audit row you can export and verify — governance of what agents do, not just what they retrieve.
Pinchy ships a deep Odoo integration: query stock, create orders, reconcile invoices, all from chat or Telegram. Acting inside an ERP is a first-class use case, not a generic connector.
amber finds and answers; its automation (amberAgents) hands the actual write-actions to external tools like n8n, Make or Zapier. Pinchy's agents draft and act in-platform — send a Telegram reply, create an Odoo record, draft an email for review — each action gated by a per-agent allow-list and captured in the signed audit. Governed action, not an ungoverned hop to a third-party automator, is the point.
Decision Guide
You're a larger organisation that wants a managed, company-wide AI search across many knowledge silos, deployed fast with no ops and a German-cloud guarantee — and search is the primary job.
You want to self-host an open-source agent platform you fully control, with per-agent governance and a signed audit, at a price a small or mid-sized team can afford — especially if Odoo is central or you need air-gap.
Do you want a managed German-cloud search assistant operated for you? That's amber. Or self-hosted, governed agents you run and own — that also act, not just answer? That's Pinchy.
FAQ
Partly — they overlap but differ in shape. amber (amberSearch) is a managed, German-cloud enterprise AI assistant and 'company GPT' built around permission-aware search across your knowledge silos. Pinchy is a self-hosted, open-source agent platform you run on your own infrastructure, with per-agent permissions and a signed audit trail. Both are GDPR-strong, but amber processes your data in its German cloud while Pinchy keeps everything on infrastructure you control.
Only at amber's Enterprise tier, which carries a 500-seat minimum. Below that, amber is cloud-only SaaS, hosted in Germany on the Open Telekom Cloud and operated by amber. Pinchy is self-hosted from day one at any size: you run it yourself with a single Docker Compose stack on your own servers, and it can run fully air-gapped with a local model via Ollama.
amber is GDPR-compliant by hosting your data in German data centres it operates, with ISO 27001 and EU AI Act alignment. Pinchy is GDPR-compliant by architecture: it runs on infrastructure you control, so data never leaves your network in the first place — and paired with a local model via Ollama it can be fully air-gapped. amber gives you a managed EU cloud; Pinchy gives you your own servers.
No. amber is a proprietary, closed-source platform. Pinchy is AGPL-3.0: you can read the code, modify it, and run it yourself — no vendor holds your data or your deployment.
Choose amber when you are a larger organisation that wants a managed, proven, company-wide AI search across many knowledge silos (SharePoint, Confluence, Microsoft 365) with a German-cloud guarantee and no infrastructure to run. Choose Pinchy when you want to self-host an open-source agent platform you fully control, with per-agent governance and a signed audit — especially for small or mid-sized teams or Odoo-centric work.
Self-host Pinchy yourself in minutes, or book a call to talk it through. Your choice.
Or email us: info@heypinchy.com