Carta AI Integration
Carta AI agents from Bonfire Terminal help manage your cap table using your Carta context and credentials, running locally on your own machine. They summarize ownership, prep equity notes, and organize stakeholder details from Slack or Telegram without exposing data to cloud SaaS.
What Bonfire can do in Carta
Real actions from the Carta API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List issuers | Issuers | GET /v1alpha1/issuers/listIssuers |
| Get cap table | Cap Table | GET /v1alpha1/issuers/getCapitalizationTable |
| List stakeholders | Stakeholders | GET /v1alpha1/issuers/listStakeholders |
| List option grants | Securities | GET /v1alpha1/issuers/listOptionGrants |
| List share classes | Securities | GET /v1alpha1/issuers/listShareClasses |
| List 409A values | Valuations | GET /v1alpha1/issuers/listFairMarketValues |
| List funds | Investors | GET /v1alpha1/investors/listFunds |
| Create draft issuer | Onboarding | POST /v1alpha1/draftIssuers/createDraftIssuer |
Carta 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
Carta — questions
Can Bonfire automate Carta?
Yes. Bonfire runs on your machine, holds your Carta credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Carta API to run the actions you ask for in chat.
Does my Carta 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.