# Qdrant: Hermes Agent plugin > Dense semantic memory for Hermes, stored in a Qdrant collection you host. Canonical: https://hermeswatcher.com/plugins/qdrant Tier: Community Official page (Nous Research): https://hermes-agent.nousresearch.com/docs/plugins/qdrant Last updated in catalog: 2026-10-16 Dense semantic memory for Hermes, stored in a Qdrant collection you host. Each turn becomes one point — user and assistant text verbatim, no LLM summarization step — embedded on-device at 384 dimensions with fastembed (ONNX; the default install is 206 MB of runtime dependencies with no torch, versus ~1.2 GB when sentence-transformers was a hard dependency) and recalled by cosine search with an optional session_id payload filter, so a result quotes what was actually said. Registers 7 tools: qdrant_search, qdrant_upsert, qdrant_recall, qdrant_collect, qdrant_prepare, qdrant_forget (point-targeted deletion, dry-run by default, no delete-all), and md_search (local markdown knowledge index). An optional recall-indicator display, display.level (off | summary | verbose, default off), adds latency and collection to the chat indicator at summary and one numeric line per operation to the log at verbose — numbers and identifiers only, never recalled message text or search-result snippets (the md_search line also echoes the query you searched — your own input, not recalled content); it is separate from the older top-level progress knob (off | minimal | verbose), which gates status events. sentence-transformers is selectable on GPU hosts; both backends produce identical vectors for all-MiniLM-L6-v2, so switching backends needs no re-embedding. A circuit breaker (5 consecutive I/O failures, 120 s cooldown) degrades to no new memories instead of crashing, and is_available()/check_backend()/unavailable_reason() distinguish a misconfiguration from a dead server. Optional hybrid dense+sparse RRF search (default off): one config key enables dense+BM25 RRF fusion. A fresh collection declares the sparse vector at creation and an existing dense-only store gets it added in place (Qdrant >= 1.18) with one bundled backfill command; measured +0.024 recall@10 on the LongMemEval 1,000-example benchmark. INT8 quantization is not implemented. Local embedded Qdrant mode is not supported: the provider is REST-only and needs a reachable server. ## Good to know before installing All memory content (verbatim user and assistant turns) is stored in and read back from the Qdrant server at the configured url (default http://localhost:6333); QDRANT_API_KEY is only needed for Qdrant Cloud, is kept in .env and read through the Hermes secret scope, and is never written to config.yaml or qdrant.json. Disclosure — the only other outbound traffic is a one-time download of the embedding model weights (plus the 10 MB Qdrant/bm25 sparse model when hybrid is on) from huggingface.co (fastembed falls back to storage.googleapis.com/qdrant-fastembed if that fails); embedding runs on-device and no memory content goes to any other party. Disclosure — settings are stored in /qdrant.json (created 0600, no credentials) and last-operation status in /qdrant-status.json. Disclosure — md_search returns snippets of local markdown to the model from ~/.hermes/skills, the Obsidian vault at ~/Documents/hermes_default, ~/.hermes/hermes-agent/website and any path in the md_docs_roots key of qdrant.json; its index is built only when you run scripts/md_ingest.py and lives in /state/md-search/ (shared by all profiles). Disclosure — the optional semant From the plugin's catalog listing. ## How to install 1. Install it. Hermes asks for any API keys it needs, then asks whether to turn it on. ```bash hermes plugins install qdrant ``` 2. Said no? Turn it on later: ```bash hermes plugins enable qdrant ``` 3. Restart Hermes so it loads the plugin. Some plugins also need a sign-in or settings: see the official page. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide: https://hermes-agent.nousresearch.com/docs/user-guide/features/plugins ## Facts - Category: Memory & notes - Maintained by: kuehnberger (Community) - Needs: No API keys declared - Adds tools: `qdrant_search`, `qdrant_upsert`, `qdrant_recall`, `qdrant_collect`, `qdrant_prepare`, `qdrant_forget`, `md_search` - Requires Hermes: `>=0.21.5` - Version: 0.1.8 - In the catalog since: 2026-10-02, updated 2026-10-16 ## Links - [Full setup and settings (official page)](https://hermes-agent.nousresearch.com/docs/plugins/qdrant) - [Source code](https://github.com/kuehnberger/hermes-qdrant-memory#readme) - [All plugins](https://hermeswatcher.com/plugins.md) --- HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt