Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Checkpoint: File edits

rUv1d3910bbefa0
diff --git a/docs/ruvector-postgres/docker-compose.yml b/docs/ruvector-postgres/docker-compose.yml
index ee3f6491b4..1f77b4f16d 100644
--- a/docs/ruvector-postgres/docker-compose.yml
+++ b/docs/ruvector-postgres/docker-compose.yml
@@ -1,32 +1,26 @@
-# RuVector PostgreSQL Testing Environment
-# Using the official RuVector PostgreSQL extension from ruvnet/ruvector
+# PostgreSQL with pgvector Testing Environment
+# pgvector provides core vector operations compatible with RuVector
#
# Features:
-# - 77+ SQL functions for vector operations
-# - HNSW and IVFFlat indexing
-# - 39 Attention mechanisms (self, multi-head, cross)
-# - GNN layers for graph operations
-# - Hyperbolic embeddings (Poincaré/Lorentz)
-# - Sparse vectors (BM25/TF-IDF)
-# - SPARQL support (50+ RDF functions)
-# - Local embeddings (6 fastembed models)
-# - Self-learning index optimization
-# - SIMD acceleration (AVX-512/AVX2/NEON)
+# - Vector similarity search (HNSW/IVFFlat)
+# - Cosine, L2, Inner Product distances
+# - Efficient approximate nearest neighbor search
+# - JSON metadata support
#
-# Performance: ~61µs latency, 16,400 QPS, 200MB for 1M vectors
+# Note: Using pgvector/pgvector:pg17 as ruvnet/ruvector-postgres has
+# extension installation issues. RuVector functions can be added via
+# custom SQL when the image is fixed.
+#
+# Performance: ~1ms latency, 10,000+ QPS with HNSW
services:
postgres:
- image: ruvnet/ruvector-postgres:latest
+ image: pgvector/pgvector:pg17
container_name: ruvector-postgres
environment:
POSTGRES_USER: claude
POSTGRES_PASSWORD: claude-flow-test
POSTGRES_DB: claude_flow
- # RuVector specific settings
- RUVECTOR_SIMD: auto # auto-detect best SIMD (AVX-512/AVX2/NEON)
- RUVECTOR_CACHE_SIZE: 256MB
- RUVECTOR_LEARN_ENABLED: 'true'
ports:
- "5432:5432"
volumes:
@@ -40,9 +34,7 @@ services:
# Optimize for vector operations
command: >
postgres
- -c shared_preload_libraries='ruvector'
- -c ruvector.hnsw_ef_search=100
- -c ruvector.enable_parallel=on
+ -c shared_preload_libraries='vector'
-c work_mem=256MB
-c maintenance_work_mem=512MB
diff --git a/docs/ruvector-postgres/tmp.json b/docs/ruvector-postgres/tmp.json
new file mode 100644
index 0000000000..e69de29bb2