Showing results for gpu servers Vector
GitHub Repo
https://github.com/mosszxc/grimoire
mosszxc/grimoire
Multi-project Knowledge Base — Graph RAG with GPU transcription, vector search, MCP server
GitHub Repo
https://github.com/angelsu/sdr-memory
angelsu/sdr-memory
Long-term memory for LLM agents using Sparse Distributed Representations — no vector DB, no GPU, no external server.
GitHub Repo
https://github.com/latenceainew/colsearch
latenceainew/colsearch
High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.
GitHub Repo
https://github.com/theesfeld/VGP
theesfeld/VGP
GPU-accelerated vector display server and desktop environment for Linux
GitHub Repo
https://github.com/DigitLib/aip
DigitLib/aip
Interactive AI Infrastructure Builder. GPU + Vector Database = Workstation/Server
GitHub Repo
https://github.com/dextera-labs/ctxengine
dextera-labs/ctxengine
GPU-accelerated vector retrieval server with FAISS and Go
GitHub Repo
https://github.com/orneryd/NornicDB
orneryd/NornicDB
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes. Then, adding intelligent features like schemas, managed embeddings, LLM reranking+inferrence, GPU accel, Auto-TLP, Memory Decay, and MCP server.
GitHub Repo
https://github.com/dhaya/ctxengine
dhaya/ctxengine
GPU-accelerated vector retrieval server with FAISS and Go
GitHub Repo
https://github.com/buckyinsfo/homelab-ai-stack
buckyinsfo/homelab-ai-stack
Self-hosted AI + GPU server homelab — local LLM inference, vector search, monitoring, and GPU mining on Debian 12, fully reproducible from bare metal via Portainer GitOps.
GitHub Repo
https://github.com/bryankthompson/mcp-server-qdrant-enhanced