Meta Ads AI assistant
A Meta Ads AI assistant that lives on your desktop, Bonfire Terminal connects to the Meta Ads API to manage campaigns, answer performance questions, and reallocate spend. Local-first design means your ad account credentials and metrics never leave your machine.
What Bonfire can do in Meta Ads
Real actions from the Meta Ads API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List campaigns | Campaigns | GET /act_{ad_account_id}/campaigns |
| Create a campaign | Campaigns | POST /act_{ad_account_id}/campaigns |
| Create an ad set | Ad Sets | POST /act_{ad_account_id}/adsets |
| Create an ad | Ads | POST /act_{ad_account_id}/ads |
| Create an ad creative | Creatives | POST /act_{ad_account_id}/adcreatives |
| Get performance insights | Insights | GET /act_{ad_account_id}/insights |
| Create a custom audience | Audiences | POST /act_{ad_account_id}/customaudiences |
| Update an object status | Objects | POST /{campaign_id} |
Meta Ads agents in action
On your machine, not a SaaS
Bonfire Terminal
- Your keys & data stay on your device
- Perpetual license — no per-seat SaaS fee
- Any connected model — Claude, GPT, Gemini or Grok
- Offline Llama for local, private reasoning
- Driven from chat you already use
Cloud AI middleman
- Keys & data pass through a third-party server
- Recurring subscription, usage caps
- Model locked to the vendor
- Yet another dashboard to log into
Meta Ads — questions
Can Bonfire automate Meta Ads?
Yes. Bonfire runs on your machine, holds your Meta Ads credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Meta Ads API to run the actions you ask for in chat.
Does my Meta Ads data go to the cloud?
Bonfire runs on your desktop and keeps your keys local — it isn't a SaaS holding your data. Only the specific request you approve is sent to your chosen AI model.
Which AI models can I use?
Any connected model — Claude, GPT, Gemini or Grok. A fully offline Llama model runs locally for private reasoning but can't reach live APIs.