on-prem-ai

Star

Here are 6 public repositories matching this topic...

ykshv / rula

Star

Local-first realtime Russian voice avatar with STT, Qwen LLM, TTS, Audio2Face, LiveKit, and VRM rendering.

Updated Sep 11, 2026
Python

svemurilv / hybrid-observability-ai

Star

Agentic framework for unified full-stack observability and cloud LLMs

mcp sre observability ai-agents opentelemetry llmops ollama on-prem-ai

Updated Jul 6, 2026
Python

sypherin / growing-memory

Star

Drop-in long-term memory for LLM apps — application-layer Memory Caching (Behrouz et al. 2026, arXiv:2602.24281). 14.6x fewer tokens at higher accuracy. 3-line API.

long-term-memory rag titans memory-caching kv-cache llm long-context local-llm retrieval-augmented-generation chatbot-memory llm-memory ai-memory context-compression subquadratic on-prem-ai

Updated Jun 8, 2026
Python

tsmith-surgexi / onprem-ai-infra

Star

On-prem GPU inference infrastructure — infra-as-code, hardening baseline, topology, and ADRs for private model serving.

ai architecture inference mlops llm-infrastructure on-prem-ai

Updated Sep 15, 2026
Shell

inhousecompute / industrial-manual-rag-eval

Star

Synthetic industrial-manual RAG evaluation pack for revisions, wrong-model traps, access boundaries, abstention, and citations

manufacturing synthetic-data rag industrial-ai retrieval-augmented-generation llm-evaluation rag-evaluation private-ai evaluation-dataset on-prem-ai

Updated Aug 11, 2026

tsmith-surgexi / llm-inference-router

Star

Health-aware, cost-optimized tiered LLM inference routing — reference architecture, ADRs, and a runnable implementation.

ai architecture inference control-plane mlops llm llm-infrastructure on-prem-ai

Updated Sep 15, 2026
Python

Add this topic to your repo

To associate your repository with the on-prem-ai topic, visit your repo's landing page and select "manage topics."

Learn more