Qdrant 1.20.1 halves cold-storage HNSW reads, 2x faster quantization, plus MCP agents
qdrant_engine · x · 2026-11-16
Vector database Qdrant shipped v1.20.1 with major performance gains, plus a push on its MCP integrations.
Performance highlights:
- 50% fewer reads during HNSW graph search on cold on-disk storage
- 2x faster Turbo8/Turbo16 quantization
- Faster HNSW graph construction for large segments with PiPNN
- Much faster multi-condition filters on cold on-disk payload indexes
- Pipelined batch searches, record streaming, and shard transfers; per-read filter cardinality estimation; faster bool/null segment opens; lower per-upsert overhead on appendable segments
Agent integration: Qdrant's MCP integrations let agents manage and monitor Qdrant Cloud clusters, inspect health/performance, search docs, and interact in natural language — MCP provides tool access while Agent Skills supply the know-how to use them.
More from coding & agent
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16
- JPMorgan shows Jarvis, its internal agent assembly line, at Interrupt NYC — LangChain · 2026-11-16
- Dev clarifies: Apple doesn't ban feature flags, only fooling App Review — talkaboutdesign · 2026-11-16
- Antigravity Matches Claude Cowork in Tests, While Gemini Tasks' Purpose Remains Unclear — sebajun2 · 2026-11-16
- One 16GB GPU runs songs, voice, images, 720p video and local RAG — all offline and open source — llama-of-death · 2026-11-16