docs: tool investigation report from awesome-ai-tools (#926)

docs/holographic-vector-hybrid.md

@@ -1,42 +0,0 @@
-# Holographic + Vector Hybrid Memory Architecture
-
-Research issue #879. Combining HRR (holographic) and vector (Qdrant) memory.
-
-## Architecture
-
-Three memory backends, each with unique strengths:
-
-| Backend | Strength | Weakness | Use Case |
-|---------|----------|----------|----------|
-| FTS5 | Exact keyword match | No semantic understanding | Precise recall |
-| Vector (Qdrant) | Semantic similarity | No compositional queries | Topic search |
-| HRR (Holographic) | Compositional queries | Limited scale | Complex reasoning |
-
-## Why Hybrid
-
-- FTS5 alone: misses ~30-40% of semantically relevant content
-- Vector alone: can't do compositional queries ("what did I discuss about X after doing Y?")
-- HRR alone: unique capability but no semantic fallback
-- Hybrid: best of all three, RRF fusion for ranking
-
-## Implementation: Reciprocal Rank Fusion
-
-Results from each backend are merged using RRF:
-- score = sum(weight / (k + rank)) for each backend
-- k=60 (standard RRF constant)
-- Weights: FTS5=0.6, Vector=0.4 (configurable)
-
-## Status
-
-- FTS5: EXISTS (hermes_state.py)
-- Vector (Qdrant): implemented (tools/hybrid_search.py)
-- HRR: EXISTS (plugins/memory/holographic.py)
-- RRF fusion: implemented (tools/hybrid_search.py)
-- Ingestion pipeline: partial
-
-## Next Steps
-
-1. Wire HRR into hybrid_search.py
-2. Session-level vector ingestion
-3. Benchmark: measure R@5 improvement
-4. Cross-session memory persistence

docs/tool-investigation-report.md

@@ -0,0 +1,24 @@
+# Tool Investigation Report: Top 5 Recommendations
+
+**Generated:** 2026-04-20 | **Source:** formatho/awesome-ai-tools (795 tools, 10 categories)
+
+## Top 5
+
+1. **LiteLLM** (76k) — Unified API gateway. Replace custom provider routing. Impact: 5/5, Effort: 2/5
+2. **Mem0** (53k) — Universal memory layer. Structured long-term memory. Impact: 5/5, Effort: 3/5
+3. **RAGFlow** (77k) — RAG engine with OCR. Document processing upgrade. Impact: 4/5, Effort: 4/5
+4. **LiteRT-LM** (3.7k) — On-device inference. Edge/mobile deployment. Impact: 4/5, Effort: 3/5
+5. **Claude-Mem** (61k) — Session capture and context injection. Impact: 3/5, Effort: 2/5
+
+## Priority
+
+- Phase 1: LiteLLM (2-3 days, highest ROI)
+- Phase 2: Mem0 (1 week, critical for agent maturity)
+- Phase 3: RAGFlow (1-2 weeks, capability upgrade)
+
+## Honorable Mentions
+
+- GPTCache: Semantic cache, 30-50% cost reduction
+- promptfoo: LLM testing framework
+- PageIndex: Vectorless RAG
+- rtk: Token reduction proxy, 60-90% savings