The "Economy Mode" for AI Compute
-
Updated
Apr 11, 2026 - Python
The "Economy Mode" for AI Compute
Self-hosted GPU cluster orchestration: deploy and serve open-source AI models on your own hardware — FastAPI control plane, worker agents, vLLM/SGLang engines and an OpenAI-compatible gateway.
Self-hosted multi-agent AI platform. Persistent labs, 40 sandboxed tools (code, web, RAG, GPU dispatcher, web3), private Qdrant + LightRAG, sandboxed code execution per lab, anti-loop detection, Ollama/vLLM/OpenAI/Anthropic adapters. Two-command Docker deploy. Apache 2.0.
Distributed document RAG with VRAM-aware workload placement across heterogeneous nodes. Four interfaces: CLI, API, MCP, Web UI.
High-performance AI infrastructure marketing site built with Next.js, Tailwind CSS, and Three.js WebGL.
Legacy version of FlockParser PDF processing system
C# / .NET management service and API for orchestrating local LLM backends, model routing, and GPU resource allocation.
Collaborative, reproducible, auditable orchestration for reading Herculaneum scrolls. Pools GPUs behind one queue, pins every checkpoint and artifact by hash, keeps geometry, CT support, model response and human review separate.
vLLM model serving on Kubernetes: GPU scheduling, Helm chart, throughput & cost-per-token benchmarks
Top Distributed Training Tools (Opensource) Star if you like it!
Nimbus is a lightweight, pull-based edge AI workload orchestrator.
Top Distributed Training Platform (Opensource) 🌟 Star if you like it! 🌟
A zero-dependency client load simulator and concurrency stress-testing utility for ZeroGate.
Top GPU Orchestration Allocation Schedulers (Opensource) Star if you like it!
Trust-weighted, cost-optimal Kubernetes scheduler plugin with zero-trust telemetry verification.
Distributed compute orchestration - consensus-aware GPU scheduling across heterogeneous infrastructure
Multi-node PyTorch DDP fine-tuning of a causal LM on Nebius GPU Kubernetes, with SkyPilot workload orchestration — a 2-node torchrun job with verified NCCL collectives.
To associate your repository with the gpu-orchestration topic, visit your repo's landing page and select "manage topics."