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 1.0.7
Released
1.0.7
Three fixes, all from one customer's report. Thank you.
The assistant now answers when the question is the first post of a new topic
It only ever watched replies. If you started a thread and mentioned the bot in the opening post — the most natural way to ask it anything — nothing happened. It now answers in both places, and cannot answer twice.
Links in answers are clickable
The assistant could not produce a working link. Written as Markdown it arrived as literal text, and turning the editor's Markdown option off changed nothing, because the whole reply was being escaped. Links now come through as real links, whether the assistant writes them as Markdown or as a plain address. Only http and https addresses are ever turned into links.
This matters most if you use the knowledge base feature: an assistant that finds the right article but cannot give you a link to it has lost most of its value.
Long API calls no longer run inside your visitors' page loads
If your community has not set up a cron job, Invision Community runs its scheduled tasks during ordinary page views — that is the default, and most self-hosted sites never change it. This app's background work makes calls to an outside service, and those calls were allowed to take a long time. On a busy moment that meant a visitor's page load, and the database connection it was holding, could be tied up for as long as the call took.
The symptom is a server that looks overwhelmed for no visible reason: PHP-FPM and MySQL both saturated, while the database itself is no bigger than it was. It is not a data problem, it is page loads being held open.
Any call made while somebody is waiting on a page is now capped at 20 seconds. Work run from a real cron job, from the command line, or from a button you pressed in the AdminCP keeps its full allowance, because nobody is being kept waiting.
Nothing to reconfigure. Install over the top. If you have not set up a cron job for your community, doing so is still worth it — it is under System, Advanced Configuration.
You may only provide a review once you have downloaded the file.
There are no reviews to display.