Kaeso
Open-source AI gateway you run yourself
- Upvotes
- 0
- DR
- 20 +17 (up) since last check
- Followers
- 0
An open-source AI gateway that lets applications talk to one API while you keep provider keys, routing, and usage under your control.
About Kaeso
Kaeso is an open-source AI gateway that runs on your own servers, providing a unified API interface for multiple AI providers. It includes single sign-on for every organization, a Rust-based gateway for request handling, and a web console for managing keys, routing, limits and logs.
The gateway translates requests through KPP, its canonical format, allowing any SDK to call any model regardless of the original API format. It supports 14 built-in providers including OpenAI, Anthropic, Cerebras, Cohere, DeepSeek, Groq, Mistral, Moonshot, Ollama Cloud, OpenRouter, QwenCloud, SpaceX, Together AI and Vercel.
Organizations can set spend and token budgets per day, month or in total, and request and token rates per minute. Every request is logged with status, tokens, cost and timing. Provider keys are encrypted with AES-256-GCM and never reach application code.
- llm routing
- rust
- budget management
- open-source
- self-hosted
- single sign-on
- api gateway
- ai-gateway
Features worth knowing
- Single sign-on with OpenID Connect and two-factor authentication
- Format translation through KPP canonical format, allowing any SDK to call any model
- Spend and token budgets with hard limits that are never skipped
- Complete request logging with status, tokens, cost, timing and content when permitted
- Encrypted provider key storage with AES-256-GCM
- Web console for managing organizations, projects, members, roles and request logs
- Stateless Rust gateway for horizontal scaling
- Support for 14 built-in AI providers
- Docker Compose deployment with Caddy, PostgreSQL, Valkey and ClickHouse
- Error reporting that names unsupported fields instead of silently dropping them
Pricing
Pricing model: Open source
Follow Kaeso and hear about their milestones, new launches and demo videos by email. Stop any time.
Kaeso metrics
| Metric | Value |
|---|---|
| Domain Rating | 20 +17 (up) since last check |
| Trust Flow | 4 no change since last check |
| Citation Flow | 19 no change since last check |
| Referring domains | 15 no change since last check |
| External backlinks | 200 no change since last check |
Ahrefs Domain Rating scanned 10 Nov 2026, updated 9 Nov 2026. Main topic: Regional/Europe (4). Majestic scanned 8 Nov 2026, updated 8 Nov 2026. Link stats via Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.
Kaeso domain facts
Reveal the domain facts
| Domain age | 1 month |
|---|---|
| Registered | |
| Expires | |
| Registrar | CloudFlare, Inc. |
| DNSSEC | Not signed |
Kaeso launch results
| Measure | At launch, then latest |
|---|---|
| Domain Rating (Ahrefs) | 3 to 20 +17 (up) since launch 8 Nov 2026, then 10 Nov 2026 |
| Trust Flow (Majestic) | 4 first measured 8 Nov 2026 |
| Referring domains (Majestic) | 15 first measured 8 Nov 2026 |
Day 2 since launch. Next receipt: day 30, 8 Dec 2026. The figures report a change; they do not say what caused it, and many things can. No figure here is a guess.
Launching something soon?
Free tips from Best Digital Launch for getting ready, launch day, the week after and what to do next.
- Set up
- On launch day
- The days after
- Beyond launch
Compare and explore
FAQ
- What makes Kaeso different from LiteLLM?
- LiteLLM is a Python proxy that reaches more providers, but Kaeso is designed for teams that want the whole company signing in to one gateway. Kaeso includes single sign-on, two-factor authentication, a web console, format translation that refuses unsupported fields instead of dropping them, a Rust gateway for performance, and hard budgets that hold. All of this is in the open-source code, not an enterprise edition.
- How does format translation work in Kaeso?
- Kaeso translates each request through KPP, its canonical format, so an OpenAI SDK can call Claude and an Anthropic SDK can call GPT. A field the target model cannot honor is refused with an error that names it, and unsupported settings are listed in the kaeso-left-out header.
- How are provider API keys stored and protected in Kaeso?
- Provider keys belong to the organization, are encrypted with AES-256-GCM under a master key ring you hold, and never reach application code. Apps only ever see their own Kaeso key. Keys come from memory and are kept for 30 seconds.
- What AI providers does Kaeso support?
- Kaeso supports 14 built-in providers: OpenAI, Anthropic, Cerebras, Cohere, DeepSeek, Groq, Mistral, Moonshot, Ollama Cloud, OpenRouter, QwenCloud, SpaceX, Together AI and Vercel. Kaeso also supports custom providers you add.
Leave a review for Kaeso
Nobody has reviewed Kaeso yet. Start things off.
A review is always free and can never be paid for. Go to the reviews and discussion
Reviews and chat · Product news · Send it on · Run this company? Claim it here · Report it
Kaeso has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link (locked)
Makers
- Devin OldenburgFounder
- Devin Oldenburg (Logicplanes)Founder
Alternatives to Kaeso
YABANIN
Self-hosted AI infrastructure with measurable returns
AI inference & GPU cloud0 votes. Log in to add your vote for YABANINQuantum Computing Inc
Putting photons to work
AI inference & GPU cloud0 votes. Log in to add your vote for Quantum Computing IncKinetic
Open-source engine for faster local language model inference with bit-for-bit identical output
AI inference & GPU cloud0 votes. Log in to add your vote for KineticLoops
Python SDK for LoRA fine-tuning with supervised fine-tuning and reinforcement learning
AI inference & GPU cloud0 votes. Log in to add your vote for Loops
