Patsnap AI Integration
Patsnap AI agents from Bonfire Terminal run on your own machine, working from your Patsnap context and stored credentials. Local-first agents help organize patent analytics, summarize prior art, and prep IP briefings without your research data ever leaving the device.
What Bonfire can do in Patsnap
Real actions from the Patsnap API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Get search result count | Patent search | POST /search/patent/query-search-count/v2 |
| Search patents by query | Patent search | POST /search/patent/query-search-patent/v2 |
| Query search and filter | Patent search | POST /search/patent/query/v2 |
| Semantic similar-patent search | Patent search | POST /search/patent/semantic-search-patent/v2 |
| Nested formula search | Patent search | POST /search/patent/nested-search-patent |
Patsnap 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
Patsnap — questions
Can Bonfire automate Patsnap?
Yes. Bonfire runs on your machine, holds your Patsnap credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Patsnap API to run the actions you ask for in chat.
Does my Patsnap 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.