π 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
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
darwin-plugins iter 3 β ruflo-rag-memory: replace remaining unverified HNSW perf table with measured audit numbers
ruv002435514564
diff --git a/plugins/ruflo-rag-memory/README.md b/plugins/ruflo-rag-memory/README.mdindex 71ca9beda5..de4f9e898d 100644--- a/plugins/ruflo-rag-memory/README.md+++ b/plugins/ruflo-rag-memory/README.md@@ -93,7 +93,7 @@ Claude Code Auto-Memory (~/.claude/projects/*/memory/*.md)βββ claude-memories namespaceββΌ (HNSW ANN index)- Semantic Search (150x-12,500x faster)+ Semantic Search (HNSW ANN β measured ~1.9x at N=20k vs brute force; see docs/reviews/intelligence-system-audit-2026-05-29.md)```## Encryption at rest (ruflo 3.6.25+)@@ -167,12 +167,15 @@ npx @claude-flow/cli@latest memory search --query "auth security" --limit 5## HNSW Performance-| Operation | Latency | vs Brute Force |-|-----------|---------|----------------|-| Vector search (100 entries) | ~0.01ms | 150x faster |-| Vector search (10k entries) | ~0.05ms | 2,500x faster |-| Vector search (100k entries) | ~0.1ms | 12,500x faster |-| Store + index | ~1ms | β |+Measured numbers from [`docs/reviews/intelligence-system-audit-2026-05-29.md`](../../docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](../../scripts/benchmark-intelligence.mjs):++| Operation | vs Brute Force | Notes |+|-----------|----------------|-------|+| Vector search (N=5k) | ~3.2xβ4.7x faster | ruvector NAPI, recall@10 ~0.99 |+| Vector search (N=20k) | ~1.9x faster | ANN wins above crossover |+| Vector search (below crossover) | ties/loses | brute force preferred for small N |++The previously published "150xβ12,500x" figures were brute-force fallback artifacts and are not reproduced under the audit harness.## Integration with ruvector