USAspending.gov AI features
USAspending.gov AI features are delivered by Bonfire Terminal, which drives the public USAspending API through device-resident AI. Agents fetch spending records, summarize contracts, and track agency budgets on demand while your queries and results remain local.
What Bonfire can do in USAspending.gov
Real actions from the USAspending.gov API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search awards | Award Search | POST /api/v2/search/spending_by_award/ |
| Count awards | Award Search | POST /api/v2/search/spending_by_award_count/ |
| Spending by category | Category Search | POST /api/v2/search/spending_by_category/ |
| Get award | Awards | GET /api/v2/awards/{award_id}/ |
| Get award funding | Awards | POST /api/v2/awards/funding/ |
| List recipients | Recipients | POST /api/v2/recipient/ |
| Get agency overview | Agencies | GET /api/v2/agency/{toptier_code}/ |
| List federal accounts | Federal Accounts | POST /api/v2/federal_accounts/ |
USAspending.gov 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
USAspending.gov — questions
Can Bonfire automate USAspending.gov?
Yes. Bonfire runs on your machine, holds your USAspending.gov credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the USAspending.gov API to run the actions you ask for in chat.
Does my USAspending.gov 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.