AI Assistant — support that answers while you sleep
Your members ask the same questions at 2am that you answer every morning. AI Assistant replies for you. Mention its account in any topic and it answers in seconds — grounded in your own community's content, in your own words, on your own terms.
It runs on your API key with your provider. No subscription to us, no per-seat pricing, no member data passing through a third party.
What it does
Answers @mentions. A member mentions the bot account in a topic and gets a real reply, posted as a real member — notifications, search indexing and counters all behave exactly as they should.
Learns from your community. Optional knowledge retrieval pulls the most relevant passages from elsewhere on your forum and gives them to the model before it answers, so replies cite what your community already knows instead of guessing.
Captures bugs and suggestions. Every answered post is classified. Bug reports and feature requests land in a triage queue in your AdminCP — and, above a confidence threshold you set, are filed straight to GitHub as issues with the forum permalink attached.
Shows you exactly what it costs. Every call is logged with token counts and real dollar cost, with a monthly budget cap that stops the assistant when it's reached.
You stay in control
Persona and house rules. A free-text field that shapes every answer — who the assistant is, what your community is about, what it must never say, and when to escalate to a human.
Choose your forums. Pick exactly which forums it answers in. Leave it unselected for all of them.
Choose your model. Anthropic (Claude) or any OpenAI-compatible endpoint — OpenAI, OpenRouter, Groq, Azure, or a model you host yourself.
Never guesses out loud. The assistant is instructed to say plainly when it doesn't know, and to ask for the detail it needs rather than inventing a setting or a version number.
Knowledge retrieval, three ways
Off — answers from the current topic alone.
Keyword — searches your community with MySQL full-text. Needs no extra API key and works the moment you switch it on.
Semantic — true meaning-based retrieval using Voyage AI or any OpenAI-compatible embeddings endpoint. Finds the right answer even when the member's words don't match your wording.
Semantic mode degrades gracefully: if the embeddings key is missing or the service is unreachable, it quietly falls back to keyword search rather than answering with nothing. New and edited posts are indexed automatically, and a background job builds the index for your existing content in batches.
Requirements
Invision Community 5.0 or newer (self-hosted), with the Forums application
An API key from Anthropic, OpenAI, or any OpenAI-compatible provider
Optional: a Voyage AI or OpenAI embeddings key for semantic retrieval
Optional: a GitHub token if you want bug reports filed automatically
Built to be safe
Slow model calls run in the background, so a member's post is never held up waiting for an answer, and a failed call never blocks a reply. The assistant will not answer its own posts, will not answer the same post twice, and stops entirely once your monthly budget is reached. It is upgrade-safe — it listens to Invision Community's own content events and never edits a single core file.
Version 1.0.0 · Invision Community 5 · self-hosted
Disclaimer: This does not search the internet to get answers as that would eat up credits. The best thing to do is setup a KB with all information or it will only give answers based on forum posts.
Edited by Ernest Defoe
Added disclaimer
What's New in Version 1.0.5
Released
Fixed — a wrong embedding model failed silently
If the Model field contained something that cannot produce embeddings — most often a chat model such as gpt-5.4-nano — Auto Tagging accepted it without complaint. "Learn tags" then reported that it was learning the vocabulary in the background, the background job hit an API error and stopped, and nothing was stored.
The result was an app that looked correctly configured, showed no errors anywhere, used no API credit, and never tagged anything. The Preview screen said "Learn the tag vocabulary first" — which is also what it says to someone who has never pressed the button, so there was nothing to tell the two situations apart.
Three changes address it.
Your embedding settings are now tested when you save them. Auto Tagging sends one short test request to your provider using the exact provider, key and model you entered. If it fails, the settings are not saved and the reason appears on the form, quoting the provider's own words. A chat model in the Model field is now refused at the moment you enter it, rather than half an hour later inside a background task. The test only runs when the provider, key or model has actually changed, so saving any other setting costs nothing.
A failed vocabulary build is now recorded and shown. The Auto Tagging settings screen displays the failure, when it happened, and the provider's message quoted in full. Previously the reason went to the system log and the background job removed itself, leaving the settings screen with nothing left to report.
Preview and Backfill now tell you which problem you have. "The last attempt to learn the tag vocabulary failed" is now a separate message from "Learn the tag vocabulary first", and it carries the reason and the time.
Also
The Model field's help text now states that it must be an embeddings model, and names a working example for each provider: text-embedding-3-small for OpenAI, voyage-3.5-lite for Voyage.
Upgrading
Adds one setting, applied automatically. No configuration changes are needed, and your existing tag vocabulary is left untouched.
You may only provide a review once you have downloaded the file.
There are no reviews to display.