Ruflo Vector Search
HNSW vector search with RaBitQ quantization via the Ruflo MCP plugin — corpus search, quantized search, hot-path routing
- What
- HNSW vector search with RaBitQ quantization via the Ruflo MCP plugin — corpus search, quantized search, hot-path routing
- Cost
- Free
- Needs
- the Ruflo MCP plugin installed and configured in your agent (this skill only calls the plugin's `mcp__plugin_ruflo-core_ruflo__*` tools — without the plugin it does nothing); an embedding engine the plugin can drive
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — vector search powered by the Ruflo plugin's MCP tools: large-scale HNSW search (`embeddings_*`, up to millions of vectors, ~0.99 recall@10), RaBitQ 1-bit quantization for 32× memory reduction on large corpora, a WASM hot-path router (`ruvllm_hnsw_*`) for up to ~11 priority patterns, plus hyperbolic embeddings for hierarchical data and cross-namespace unified search. By @ruvnet, listed here with credit to its creator. Honest caveats: requires the Ruflo MCP plugin installed and configured in your agent — the skill is an instruction layer over the plugin's `mcp__plugin_ruflo-core_ruflo__*` tools and does nothing without it; pick the right path for your scale (corpus search vs hot-path router — they are not interchangeable). Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Ruflo Vector Search is a free Muse skill for vector search powered by the Ruflo plugin's MCP tools. It offers large-scale HNSW search with up to millions of vectors and about 0.99 recall at 10, RaBitQ 1-bit quantization for 32 times memory reduction on large corpora, and a WASM hot-path router for priority patterns, plus hyperbolic embeddings.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 58e0ae7Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: the Ruflo MCP plugin installed and configured in your agent (this skill only calls the plugin's `mcp__plugin_ruflo-core_ruflo__*` tools — without the plugin it does nothing); an embedding engine the plugin can drive Install "Ruflo Vector Search" for me. Teach my agent the vector-search workflow — status check, init, generate, search, compare — and which path to pick: large-scale embeddings_search, RaBitQ quantized search (≥5,000 vectors), ruvllm WASM hot-path router (≤11 patterns), hyperbolic embeddings, unified cross-namespace search Repository: https://raw.githubusercontent.com/ruvnet/ruflo/58e0ae7e14e68aab45a4127d6f42f567bbcfb328/plugins/ruflo-agentdb/skills/vector-search/SKILL.md Pinned version: install the code at commit 58e0ae7e14e68aab45a4127d6f42f567bbcfb328 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the ruvnet-ruflo-vector-search skill from the repository into a temporary folder 2. Safety check: review the SKILL.md for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md into the agent's skills directory, in a folder named "ruvnet-ruflo-vector-search". 4. Verify with no network calls: frontmatter valid, files in place, and confirm the Ruflo MCP plugin tools are available to the agent. 5. Report what was installed, where, and what I still need to do myself (e.g. install/configure the Ruflo MCP plugin if not already done). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 58e0ae7 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.