Back to Ruflo

ruflo-ruvector

plugins/ruflo-ruvector/README.md

3.6.3011.2 KB
Original Source

ruflo-ruvector

Self-learning vector database powered by [email protected] — HNSW, Adaptive LoRA embeddings, hooks-based intelligence, SONA self-optimizing patterns, brain (collective knowledge), and 103 MCP tools.

Pinned version: this plugin targets [email protected]. Earlier 0.1.x versions are missing several commands (brain, route, sona); some legacy docs referenced 2.x features that do not exist on npm. Always invoke with the pin.

Overview

Wraps the ruvector npm package as a Ruflo plugin, providing vector embedding, semantic search, code-graph clustering, hyperbolic projection, self-learning hooks, and SONA / Brain diagnostics. ruvector's Rust backend delivers sub-millisecond queries and 52,000+ inserts/sec.

Prerequisites

bash
# Required
npm install [email protected]

# Optional add-ons (install as needed)
npm install ruvector-onnx-embeddings-wasm   # required for `embed text` to work
npm install @ruvector/pi-brain              # required for `brain` subcommands
npm install @ruvector/ruvllm                # required for `sona` subcommands (JS fallback)

Run a health check:

bash
npx -y [email protected] doctor

Installation

bash
claude --plugin-dir plugins/ruflo-ruvector

MCP Integration (103 Tools)

Register with the pinned version:

bash
claude mcp add ruvector -- npx -y [email protected] mcp start

Key tool categories: hooks routing, AST analysis, diff classification, coverage routing, graph clustering, security scanning, RAG context, brain knowledge, SONA learning.

Agents

AgentModelRole
vector-engineersonnetEmbedding, HNSW indexing, code-graph clustering, hyperbolic projection, hooks routing, brain/SONA

Skills

SkillUsageDescription
vector-setup/vector-setup [--full]First-run installer: pins [email protected], adds ONNX/Brain/SONA/router add-ons, registers MCP, runs doctor
vector-embed/vector-embed <text>ONNX embeddings (384-dim) via embed text
vector-cluster/vector-cluster <files...>Spectral/Louvain code-graph clustering via hooks graph-cluster
vector-hyperbolic/vector-hyperbolic <text>Standard ONNX embed + Poincare projection in user code

Commands (/vector slash command)

The full surface is documented in commands/vector.md (80+ subcommands). Quick reference:

bash
# Embedding
/vector embed <text>                 # ruvector embed text "<text>"
/vector embed-adaptive <text>        # ruvector embed text "<text>" --adaptive --domain code
/vector embed-file <path>            # read file, pass content as text
/vector embed-benchmark              # ruvector embed benchmark

# Database lifecycle
/vector db create <path>             # ruvector create <path> -d 384 -m cosine
/vector db stats <path>              # ruvector stats <path>
/vector insert <db> <json>           # ruvector insert <db> <json>
/vector search <db> <vector-json>    # ruvector search <db> -v <json> -k N
/vector export <db>                  # ruvector export <db> -o backup.json
/vector import <file>                # ruvector import <file> -d <database>

# RVF cognitive containers (45 example stores)
/vector rvf create|ingest|query|status|segments|derive|compact|export|examples|download

# GNN + attention (real native bindings)
/vector gnn info|layer|search|compress
/vector attention list|compute|benchmark|hyperbolic|info

# Code intelligence (hooks)
/vector ast <file>                   # ruvector hooks ast-analyze <file>
/vector hooks ast-complexity <files...>
/vector hooks coverage-route <file> | coverage-suggest <files...>
/vector hooks rag-context <query>
/vector hooks route|route-enhanced|suggest-context
/vector cluster <files...>           # ruvector hooks graph-cluster <files>
/vector hooks security-scan <files...>
/vector hooks diff-analyze|diff-classify|diff-similar [commit]
/vector hooks remember|recall <query>
/vector hooks coedit-record|coedit-suggest|error-record|error-suggest
/vector hooks trajectory-begin|trajectory-step|trajectory-end

# Native + workers
/vector native list|run <type>|benchmark|compare
/vector workers triggers|presets|phases|dispatch|status|...

# Collective intelligence
/vector brain status|search|share|list|drift|partition|transfer|sync|page  (needs @ruvector/pi-brain)
/vector sona status|info|stats|patterns|train|export                       (needs @ruvector/ruvllm)
/vector llm models|embed|benchmark|info                                    (needs @ruvector/ruvllm)

# Identity + edge compute (pi network)
/vector identity generate|show|export|import
/vector edge status|balance|tasks|join|dashboard

# Server / decompile / demo / system
/vector server [-p 8080] [-g 50051]
/vector decompile <npm-pkg-or-file-or-url>
/vector demo --basic | --gnn | --graph
/vector doctor | info | benchmark | install | setup

End-to-End Example: store + search project files

bash
# 0. One-time setup
/vector-setup

# 1. Create a database
npx -y [email protected] create project.db -d 384 -m cosine

# 2. Embed every TypeScript source file (loop — no built-in --batch)
mkdir -p .vec
for f in $(find src -name '*.ts'); do
  npx -y [email protected] embed text "$(cat "$f")" -o ".vec/${f//\//_}.json"
done

# 3. Insert all embeddings (assumes a JSON array of {id, vector, metadata})
jq -s '[.[] | {id: input_filename, vector: .vector}]' .vec/*.json > corpus.json
npx -y [email protected] insert project.db corpus.json

# 4. Search by query embedding
QV=$(npx -y [email protected] embed text "JWT refresh-token rotation" --output -)
npx -y [email protected] search project.db -v "$QV" -k 5

# 5. Inspect index health
npx -y [email protected] stats project.db

For an alternative store format with lineage tracking, replace steps 1–3 with:

bash
npx -y [email protected] rvf create project.rvf
npx -y [email protected] rvf ingest project.rvf < corpus.json
npx -y [email protected] rvf query project.rvf

Capabilities ([email protected], verified)

FeatureCLINotes
HNSW searchsearch <db> -v ... -k N~0.045ms latency
Adaptive LoRA embeddingsembed text "..." --adaptive --domain codeLoRA-tuned
Distance metricscreate <path> -m cosine|euclidean|dotset at create time
RVF cognitive containers`rvf createingest
Attention mechanismsattention listDotProduct, MultiHead, Flash, Hyperbolic, Linear, MoE, GraphRoPe, EdgeFeatured, DualSpace, LocalGlobal
GNN ops`gnn layersearch
Code-graph clusteringhooks graph-cluster <files>spectral / Louvain
Diff embeddings`hooks diff-analyzediff-classify
Coverage-aware routing`hooks coverage-routecoverage-suggest`
RAG contexthooks rag-context "query"works in CLI and MCP
AST analysis`hooks ast-analyzeast-complexity`
Self-learning loop`hooks rememberrecall
Native workers`native listrun <security
Background workers`workers dispatchstatus
Decompile npm/JSdecompile <target>inspect upstream packages
Serverserver -p 8080HTTP/gRPC mode
Demo`demo --basic--gnn
Identity (pi key)`identity generateshow
Edge compute`edge statusbalance

Known limitations / bugs in 0.2.25

IssueDetailWorkaround
ONNX runtime missingembed textONNX WASM files not bundlednpm i ruvector-onnx-embeddings-wasm (see /vector-setup)
optimizeSelf-reports "not yet shipped in this release"none — track upstream issue 401
hooks force-learnTypeError intel.tick is not a functionrun a real trajectory via trajectory-begin/step/end
hooks graph-mincutCannot read properties of undefined (reading 'length')use hooks graph-cluster
hooks git-churnFails outside a git reporun from inside the repo
benchmarkSome installs fail with Missing field 'dimensions'use attention benchmark or gnn search benchmarking
cluster (top-level)Status: Coming Soonuse hooks graph-cluster
compare, top-level index, midstream, embed --file/--batch/--glob/--model poincareDon't existsee commands/vector.md for replacements

Self-Learning Hooks

bash
# Full pretrain pipeline + agent generation
npx -y [email protected] hooks init --pretrain --build-agents quality

# Smart agent routing (positional task!)
npx -y [email protected] hooks route "implement OAuth flow"
npx -y [email protected] hooks route-enhanced "fix CVE-2025-1234"

# Code analysis (positional file!)
npx -y [email protected] hooks ast-analyze src/module.ts
npx -y [email protected] hooks diff-analyze HEAD
npx -y [email protected] hooks coverage-route src/module.ts
npx -y [email protected] hooks security-scan src/

Brain (Collective Knowledge)

bash
npm install @ruvector/pi-brain   # required dependency

npx -y [email protected] brain status
npx -y [email protected] brain search "authentication patterns"
npx -y [email protected] brain list
npx -y [email protected] brain drift code   # knowledge drift for a domain

SONA (Self-Optimizing Neural Architecture)

bash
npx -y [email protected] sona status
npx -y [email protected] sona patterns "auth refactor"
npx -y [email protected] sona stats

Performance

OperationLatencyNotes
HNSW search~0.045ms8,800x vs ONNX inference
Memory cache~0.01ms40,000x vs ONNX inference
Insert52,000+/secRust backend (@ruvector/core)
Memory per vector~50 bytesEfficient storage

Known Caveats

  • ONNX runtime not bundled by defaultembed text will report ONNX WASM files not bundled until you install ruvector-onnx-embeddings-wasm.
  • No --file, --batch, --glob, --namespace, --k, --task, --model poincare flags — these were in older docs but never shipped in 0.2.25. See agents/vector-engineer.md for the replacement table.
  • brain requires @ruvector/pi-brain — install separately.
  • sona requires @ruvector/ruvllm — install separately (the native binding is not always present in the npm tarball).
  • Top-level cluster is "Coming Soon" — for actual clustering use hooks graph-cluster <files>.
  • compare, midstream, top-level index subcommands do not exist.

Architecture Decisions

Smoke test

bash
bash plugins/ruflo-ruvector/scripts/smoke.sh
# Expected: "11 passed, 0 failed"
  • ruflo-agentdb — HNSW storage backend in AgentDB
  • ruflo-intelligence — SONA pattern learning integration
  • ruflo-knowledge-graph — Graph RAG for multi-hop retrieval
  • ruflo-rag-memory — Simple semantic search via ruvector

License

MIT