PACER / CourtListener AI Integration
PACER / CourtListener AI agents in Bonfire Terminal aid legal research using your own account context and credentials. They pull case context, summarize dockets, and organize findings from a local-first desktop app, keeping research work on your own machine.
What Bonfire can do in PACER / CourtListener
Real actions from the PACER / CourtListener API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search case law and dockets | Search | GET /api/rest/v4/search/ |
| List dockets | Dockets | GET /api/rest/v4/dockets/ |
| List docket entries | Docket Entries | GET /api/rest/v4/docket-entries/ |
| List opinions | Opinions | GET /api/rest/v4/opinions/ |
| List opinion clusters | Clusters | GET /api/rest/v4/clusters/ |
| List judges/people | Judges | GET /api/rest/v4/people/ |
| Resolve citations | Citation Lookup | POST /api/rest/v4/citation-lookup/ |
| Fetch PACER document | RECAP Fetch | POST /api/rest/v4/recap-fetch/ |
PACER / CourtListener 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
PACER / CourtListener — questions
Can Bonfire automate PACER / CourtListener?
Yes. Bonfire runs on your machine, holds your PACER / CourtListener credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the PACER / CourtListener API to run the actions you ask for in chat.
Does my PACER / CourtListener 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.