Governed AI coding for engineering teams

Ship AI code. Keep control.

One gateway for Claude, GPT, Gemini, NVIDIA and Ollama — with budgets, model policy, secret filtering and a full audit trail of who changed what and why. Bring your own provider keys — you're never marked up on tokens.

Your code only reaches the providers you approve — nothing else.

Bring your own keys VS Code extension Change audit trail Provider failover Governed agents
Gatway · VS Code
Workspace scanned · 312 files · .aiconfig applied
Analyzed with llama-3.1-8b · prompt optimized · target: validate_token()
Focused context · 2.9k chars sent instead of 34k
Security filter · 1 secret redacted before send
Streaming from claude-sonnet-4-5
Proposed edits · 2 files · awaiting approval
Cost this request $0.01191% saved vs full-context · logged to audit
The core idea

A cheap model narrows the problem.
The expensive one solves it.

Most AI coding tools throw your whole repository at a frontier model and bill you for it. Gatway does the thinking about what to send first — so you pay for the code that matters.

01

Analyze & optimize

A small, cheap model rewrites the prompt for clarity and asks a clarifying question if the request is ambiguous — before a single expensive token is spent.

02

Locate the code

It identifies the exact files and functions involved. Your editor slices out just those symbols — not the first 5,000 characters of five files.

03

Send only what matters

The optimized prompt plus the targeted code goes to the strong model. Typical requests drop from ~34k characters to ~3k.

04

Apply & record

Changes come back as a reviewable diff. Approve, and the edit is applied and written to the audit trail with the prompt that caused it.

~90%
less context sent per request
5
providers behind one endpoint
100%
of AI-assisted changes audited
Platform

Everything your team needs.
Everything your CTO asks for.

Inline autocomplete

Ghost-text completions as you type, routed to a fast model of your choosing — including a local one, so keystrokes never leave the machine.

Edit with diffs

The model proposes changes; you see a native diff and approve. Nothing is written to disk without a human clicking Apply.

AI code review

Review any diff or pull request against your project rules. Structured findings with severity, file, line and a concrete fix. Works from CI too.

🤖

Governed agents

Declarative agents that explore the codebase and propose multi-file changes. Tool allowlists are enforced by the gateway — a read-only agent truly cannot write.

🛡

Secret & PII filter

Outbound prompts are scanned for keys, tokens and PII. Log, redact or block them — per organization policy, before anything reaches a provider.

📊

Change audit trail

Every prompt and every applied change, with the full diff, attributed to a developer and a project. Leads can answer "who changed this, and why?".

💸

Cost controls

Semantic response cache, context optimizer, focused context and cheap-vs-strong routing — plus hard monthly budgets per org, project and user.

🔀

Provider failover

Rate limit or outage on one provider? Requests fail over to the next model in your chain automatically. Your team never sees it.

🔑

Bring your own keys

Your Anthropic, OpenAI, Gemini and NVIDIA keys, encrypted at rest. Your vector database. Your server. We never sit in the middle.

Security & compliance

Built for teams that can't just paste code into a SaaS.

Approve the providers, set the policy, and get the evidence trail your security review will ask for.

Bring your own provider keysYour Anthropic, OpenAI, Gemini and NVIDIA keys, encrypted at rest — we never see your token spend.
Policy enforcementAllowed-model lists, per-user token limits and monthly budgets, enforced at the gateway.
Role-based accessDeveloper, lead, FDE and admin roles. The audit log is visible to leads, not to peers.
Keys encrypted at restProvider credentials are sealed and never stored or logged in plaintext.
Local model optionPoint a project at Ollama and that code path never reaches a third-party provider.
Changes · audit
14:22priya@acme
"add rate limiting to the login route"
api/auth.py +34 −6
claude-sonnet-4-5 · approved & applied
14:05sam@acme
"refactor the payment retry loop"
blocked · secret detected in context
Pricing

Simple pricing. You pay providers directly.

Gatway sits between your team and the model providers — bring your own keys and we never mark up your tokens.

Team

Everything a development team needs to ship AI-assisted code with control.

  • Unlimited developers
  • All providers, your own keys
  • VS Code extension, agents, code review
  • Cost dashboard & change audit
  • Email support
Get Started

Enterprise

For organizations that need identity integration, onboarding support and an SLA.

  • Everything in Team
  • SSO / SAML and directory sync
  • Onboarding & migration support
  • Custom agents and policy design
  • Priority support with an SLA
Contact Sales

Ship AI code. Keep control.

Connect your providers, install the VS Code extension, and get a full audit trail of every AI-assisted change — usually running in minutes.

Questions? Email hello@gatway.ai