intentee/paddler

Open-source LLM load balancer and serving platform for self-hosting LLMs at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

64
/ 100
Established

Paddler helps product and DevOps teams self-host large language models (LLMs) on their own infrastructure, instead of relying on external providers. It takes open-source LLMs and serves them efficiently and reliably, allowing you to integrate AI features into your products while maintaining control over data privacy, costs, and performance. Product leaders and engineers concerned with scaling AI features will find it useful.

1,478 stars. Actively maintained with 58 commits in the last 30 days.

Use this if you need to run LLM inference and embeddings at scale within your own organization, particularly for product features or sensitive data, and want predictable costs and reliability.

Not ideal if you prefer to use managed LLM services from cloud providers and are not interested in maintaining your own infrastructure for AI models.

LLM deployment AI infrastructure DevOps data privacy cost control
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,478

Forks

84

Language

Rust

License

Apache-2.0

Category

llm-api-gateways

Last pushed

Mar 12, 2026

Commits (30d)

58

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/intentee/paddler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.