intentee

    intentee/paddler

    Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale πŸ“πŸ¦™ 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.

    ai
    llm
    networking
    llamacpp
    llmops
    load-balancer
    Rust
    Apache-2.0
    1.7K stars
    97 forks
    1.7K GitHub watchers
    Updated Oct 28, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    No releases in the last 90 days; the most recent was 101 days ago, with 12 contributors on GitHub.

    Gained 63% fewer stars in the last 90 days than in the 90 days before.

    Use Cases & Benefits

    • Provides an open-source platform for load balancing and serving large language and vision models on self-hosted infrastructure.
    • Simplifies deployment with fewer components and integrates tightly with the ggml ecosystem for efficient CPU and GPU inference.
    • Use for building scalable, private LLM inference services within organizations requiring full control over their AI models.
    • Use for DevOps teams needing dynamic autoscaling and request buffering to optimize resource usage in multi-agent LLM clusters.
    • Use for organizations in regulated industries to maintain compliance and predictable costs by self-hosting sensitive AI workloads.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Digital products and their users need privacy, reliability, cost control and an option to be independent from third party vendors.

    Paddler is an open-source LLMOps platform for organizations that host and scale open-source models in their own infrastructure.

    Excerpt from the intentee/paddler README on GitHub (Apache-2.0 license). Β© its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    97+5

    Open issues

    30+3

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    intentee/paddler compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    thedotmack/claude-mem113.6K+8.8K35today
    D4Vinci/Scrapling98.1K+6.9K651 day ago
    Leonxlnx/taste-skill110.7K+5.2K551 day ago
    calesthio/OpenMontage77.2K+4.2K40β€”
    heygen-com/hyperframes79.6K+4.1K45today
    intentee/paddler1.7Kβ€”33101 days ago
    Category median98.1K+5.2K45β€”

    Discover Repositories

    Search across tracked repositories by name or description