
SAM.gov AI Integration
SAM.gov AI agents from Bonfire Terminal pull federal contracting data via the SAM.gov API to surface relevant opportunities, entity records, and exclusions. The agents run on your own machine, using SAM.gov as a context source while keeping your research on-device.
What Bonfire can do in SAM.gov
Real actions from the SAM.gov API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search entities | Entity | GET /entity-information/v4/entities |
| Extract entities | Entity | POST /entity-information/v4/entities |
| Search opportunities | Opportunities | GET /opportunities/v2/search |
| Get notice description | Opportunities | GET /opportunities/v1/noticedesc |
| Search exclusions | Exclusions | GET /entity-information/v4/exclusions |
| Download exclusions | Exclusions | GET /entity-information/v4/download-exclusions |
| Search organizations | FederalHierarchy | GET /federalorganizations/v1/orgs |
| Get org hierarchy | FederalHierarchy | GET /federalorganizations/v1/org/hierarchy |
SAM.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
SAM.gov — questions
Can Bonfire automate SAM.gov?
Yes. Bonfire runs on your machine, holds your SAM.gov credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the SAM.gov API to run the actions you ask for in chat.
Does my SAM.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.