100% local · no cloud required

Your support inbox.
Answered by your own AI.

SupportFlowAI reads incoming support emails, searches your own, already-answered mailbox archive for the matching solution, and proposes a reply — as a draft for approval or, when confidence is high, fully automatically. All processing runs locally via Ollama; no request content ever leaves your infrastructure.

View installation → Explore features

Self-hosted · .NET 10 · Ollama · SQLite — no registration, no credit card

Why SupportFlowAI?

Not a chatbot. An inbox that thinks along.

SupportFlowAI doesn't replace a knowledge base you'd have to painstakingly populate — it learns from the replies your team has already been writing all along.

🔒
Fully local

The language model and embeddings run via a locally hosted Ollama service. Customer inquiries, mailbox content, and generated replies never leave your infrastructure — no external AI cloud API anywhere in the processing path.

OllamaNo cloud required
🧵
Learns from real threads

Instead of manually maintained FAQ articles, SupportFlowAI analyzes your existing mailbox: every answered inquiry (inbox + sent) becomes a question/answer pair for knowledge search — matched via mail threading headers, not text recognition.

IMAP threadingEML/MBOX import
🕶️
Built-in PII masking

Names, email addresses, and other personal data are automatically masked before being stored as knowledge — the training corpus never contains unmasked customer data in plain text.

Automatic masking
👀
Humans stay in the loop

In draft mode, every generated reply lands in a review queue — it's only sent once a staff member approves it. Full automation is optional and deliberately made harder to enable.

Review queueFull automation optional
📜
Complete audit log

Logins, approvals, rejections, and especially every activation/deactivation of full automation are logged immutably — you can always trace who decided what, and when.

Audit log
⚙️
Adapts to your hardware

CPU or GPU mode for the Ollama models, three vector index tiers ranging from minimal RAM usage to maximum throughput — SupportFlowAI runs just as well on a small test server as on powerful hardware.

CPU/GPULean/Balanced/Performance
How it works

From email to reviewed reply
in four steps

The entire process runs automatically in the background — you only step in where it's actually needed.

Connect your mailbox

Set up an IMAP account or an existing EML/MBOX archive as a source. A built-in connection test checks credentials and reachability immediately upon saving.

Learn automatically

The background service compares inbox and sent folders, builds question/answer pairs from existing threads, masks personal data, and computes embeddings for knowledge search.

Get a suggested reply

When a new customer inquiry arrives, SupportFlowAI searches for the best-matching known answers and has the local language model draft a reply from them.

Review or send automatically

In draft mode, you approve every reply in the review queue. Above a configured confidence threshold, full automation can handle sending without any manual step.

A few details that matter
Connection test

See instantly whether the credentials work

When creating or saving an account, SupportFlowAI automatically checks whether an IMAP/SMTP connection actually succeeds — including a plain-language error message in the account overview, instead of failing hours later at the next sync.

  • IMAP and SMTP connection test in a single step
  • Failure reason visible right away, not just "failed"
  • Manual retest button, triggerable at any time
Support-DE Connected
Archive Import Directory unreachable
Support-EN Last tested: 09:41
Automatic sync

Runs in the background — or doesn't

Periodic mailbox syncing can be turned on and off and its interval freely configured, without restarting the application. If you prefer to import exclusively by hand, just switch it off.

  • On/off switch, takes effect immediately
  • Freely selectable interval (default: 5 minutes)
  • Status visible in the system health dashboard
Automatic syncActive
Interval5 min
Vector index tiers

From test server to large knowledge base

Three operating modes for knowledge search: Performance keeps everything in memory for maximum throughput, Balanced works with a limited cache, Lean needs minimal RAM for modest test hardware.

  • Adapts to the available hardware, not the other way around
  • Switchable via a single configuration line
PerformanceIn-memory
BalancedCached
LeanFrom disk
Documentation

Everything you need to get started

Ready to try it?

Set up in a few minutes, entirely on your own infrastructure

.NET 10, Ollama, and a SQLite database are all you need to get started — no separate database system, no external cloud connection.

Open installation guide →