One enforcement layer for your AI.

Star2.2k

One enforcement layer for your AI.

Hard budget caps, real-time spend attribution, and zero model-data egress - enforced before a request hits a model.

Try the agentTalk to us

`curl -fsSL https://github.com/getkimchi/kimchi/releases/latest/download/install.sh | bash`

"Kimchi is fundamentally changing how our engineering team thinks about AI-assisted development. The multi-model approach keeps the quality of a single frontier model while cutting token costs dramatically."

Dekel ShavitSr. Director of Engineering

Set the rules once. Kimchi enforces them everywhere.

Every agent request passes through one enforcement layer for spending, data, deployment, and model routing.

Agent request

Kimchi enforcement

Verified delivery

Hard spending limits

Set caps by user, team, API key, or model. Spending stops at the limit.

Your perimeter

Deploy in Kubernetes on AWS, GCP, Azure, or on-premises. Keep model data inside.

Private by architecture

Prompts, code, and outputs are excluded from model training.

Your AI. Under your control.

Set spending limits, track every dollar, and keep your code and data within your boundaries - all in one platform.

GovernanceCost visibilityData sovereignity

Spend limits for total ease of mind.

See exactly who, what, and where your AI spend is going. Per-developer, per-team, per-model, per-tag - in real time. Hard budget caps at every level: user, team, API key.

• Per API key set limits for CI/CD pipelines, bots, or contractors
• Per user every developer has their own budget with real-time visibility
• Per team finance gets a clean number; engineering keeps shipping

Many models.

Kimchi brings multiple models together to plan, build, and review your code, matching each step to the right model.

Try the agent

Built for speed. Governed by default.

One governed AI coding platform, built around the way each team already works.

Platform engineering

Run it your way

Start serverless or deploy inside your VPC.

Developers

Keep your workflow

Use Kimchi from the coding tools your team already relies on.

Your coding toolsKimchiYour models

Security teams

Govern every request

Spending policy enforced before a request leaves your environment.

Enterprise controls backed by Cast AI's security program

Security, compliance, and control aren't afterthoughts. Every feature ships enterprise-ready.

Get started in 60 seconds with control from day one.

Install the CLI, run /ferment, and hand off to the agent. No lock-in, no credit card.

Try the agentBook a demo

`curl -fsSL https://github.com/getkimchi/kimchi/releases/latest/download/install.sh | bash`