Now in private beta

The terminal that does the work.

Bang is an AI-native terminal with a real agent inside — it runs commands, reads and edits your files, and finishes the task. Bring your own models, or run them fully self-hosted. Own your backend and your data.

No spam. Just your invite when it's ready.
bang — ~/project
 bang "add rate limiting to the login route"

● agent reading src/routes/auth.js
● agent grep "loginHandler" → 2 matches
● agent editing src/routes/auth.js +18 −2
● agent running npm test ✓ 42 passing

✓ Done. Added a 5 req/min limiter and a test.
 

Works with OpenAI, Anthropic, Google, and any OpenAI-compatible endpoint — Ollama, vLLM, or your own gateway.

Not autocomplete. An agent.

Bang closes the loop — it plans, runs tools on your machine, checks its work, and keeps going until the task is done.

Agentic tool loop

Runs shell commands, reads files, greps your codebase, and applies edits — with your approval — then verifies the result. Real actions, not suggestions.

🧩

Bring your own models

Point Bang at OpenAI, Anthropic, Google, or any OpenAI-compatible endpoint. Configure providers right in the UI — no JSON files to hand-edit.

🔒

Own your backend

Bang's harness is self-hostable. Run inference against models on your own infrastructure and keep every conversation on servers you control.

🚀

Fast & native

Built on a GPU-accelerated, Rust-based terminal. Blocks, workspaces, and a keyboard-first UI that keeps up with you.

👥

Built for teams

Accounts, workspaces, and shared configuration — so your whole team runs the same agent against the same guardrails.

🛡️

You stay in control

Every command the agent wants to run is shown for approval. Nothing touches your machine without a green light.

Your models. Your rules.

Frontier APIs when you want the best. Self-hosted models when you need privacy, cost control, or offline. Switch anytime — Bang doesn't lock you in.

  • Hosted: OpenAI, Anthropic, Google
  • Self-hosted: Ollama, vLLM, and any OpenAI-compatible server
  • Per-provider keys, added and managed from the app
  • Keep sensitive code on models that never leave your network
OpenAI
Anthropic
Google
Ollama
vLLM
Self-hosted

From prompt to done in three steps

1

Ask

Describe the task in plain language, right in your terminal.

2

Approve

Bang plans, then shows each command and edit before it runs anything.

3

Ship

It executes, checks the result, and iterates until the job is finished.

Get early access to Bang

We're onboarding teams in waves. Drop your email and we'll send your invite.

We'll only email you about Bang.