5-Lens Empirical Quadrants, Pareto Frontier & 17-Facet AI Catalog
Replaces subjective analyst pay-to-play quadrants with reproducible telemetry across LLMs, CPU/Edge SLMs, 3D/Multimodal, Time-Series Foundation Models (Chronos-Bolt, TimesFM 2.0, Moirai-MoE, TimeGPT, PatchTST, Toto), Agent SDKs/Orchestrators, 7-Stage RAG, DSPy, Embeddings, MCP + A2A, Security, Tracing vs Evaluation, Memory Policies vs Vector/SQL Substrates, and Durable Execution.
All 17 Facets (10) agent_development_orchestration ai_security_and_guardrails automation_ipaas_dag_durable embeddings_and_rerankers evaluation_and_regression_testing llm_frontier_cloud llm_open_weights_cloud memory_behavior_policies multimodal_vision_audio_3d observability_tracing_monitoring programmatic_prompt_workflow_optimization protocols_mcp_and_a2a rag_context_pipeline slm_cpu_edge_quantized teleon_team_simulation_provenance timeseries_foundation_models vector_and_transactional_storage
5 Orthogonal Ranking Lenses
- Lens 1 (Empirical 2x2 Quadrant): X = Verified Execution Reliability vs Y = Architectural Composability and Governance Fit.
- Lens 2 (Constraint-Weighted Wave): Custom workload weights plus Tversky hard vetoes (
spdx_license, blast class, CPU-only). - Lens 3 (Exact Pareto Frontier): Non-dominated set across Quality, Latency, Cost, Cliff Retention, and Lock-in Freedom (orange nodes).
- Lens 4 (Jagged-Frontier Cliff Index): Perturbed neighbor retention ratio.
- Lens 5 (Team Marginal Value / WAR): Paired holdout lift net of coordination token tax.
| Component & Publisher | Primary Facet | Quadrant & Frontier | Lens Scores | Cliff & WAR | License |
|---|---|---|---|---|---|
| bm25s (Scipy Sparse Lexical) xhluca ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER PARETO | Exec: 98, Fit: 95, Wave: 94.04 | Cliff: 95%, WAR: +0.26 | MIT |
| Chonkie Semantic & Token Chunker Chonkie ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER | Exec: 97, Fit: 95, Wave: 93.16 | Cliff: 95%, WAR: +0.23 | MIT |
| deepset Haystack 2 deepset ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER PARETO | Exec: 93, Fit: 92, Wave: 92.04 | Cliff: 87%, WAR: +0.24 | Apache-2.0 |
| LlamaIndex Core LlamaIndex ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER PARETO | Exec: 90, Fit: 90, Wave: 91.42 | Cliff: 84%, WAR: +0.22 | MIT |
| Marker PDF-to-Markdown VikParuchuri / Datalab ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER PARETO | Exec: 92, Fit: 92, Wave: 89.88 | Cliff: 89%, WAR: +0.23 | GPL-3.0 |
| RAGFlow InfiniFlow ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER | Exec: 87, Fit: 82, Wave: 89.42 | Cliff: 84%, WAR: +0.2 | Apache-2.0 |
| Unstructured Unstructured.io ( rag_component) |
rag_context_pipeline |
EMPIRICAL_LEADER | Exec: 88, Fit: 82, Wave: 89.34 | Cliff: 84%, WAR: +0.18 | Apache-2.0 |
| LangChain Retrieval & Loaders LangChain ( rag_component) |
rag_context_pipeline |
OPERATIONAL_WORKHORSE | Exec: 86, Fit: 80, Wave: 88.88 | Cliff: 77%, WAR: +0.16 | MIT |
| Microsoft GraphRAG Microsoft ( rag_component) |
rag_context_pipeline |
OPERATIONAL_WORKHORSE | Exec: 82, Fit: 79, Wave: 86.69 | Cliff: 78%, WAR: +0.19 | MIT |
| EmbedChain Mem0 / EmbedChain ( rag_component) |
rag_context_pipeline |
OPERATIONAL_WORKHORSE | Exec: 82, Fit: 79, Wave: 83.12 | Cliff: 77%, WAR: +0.11 | Apache-2.0 |