17-Facet AI & Agentic Capability Catalog
Separates model providers, weights, repositories, CPU/cloud runtimes, time-series foundation models, 3D/multimodal models, agent SDKs vs orchestrators vs managed services, 7-stage RAG, DSPy optimizers, MCP + A2A protocols, guardrails, tracing vs evaluation, memory policies vs vector/SQL substrates, and durable execution.
All 17 Facets (187) 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 team_simulation_provenance timeseries_foundation_models vector_and_transactional_storage
| Component & Publisher | Primary Facet | Capability Tags | Blast & SPDX | Deployment Modes |
|---|---|---|---|---|
| NVIDIA NeMo Guardrails NVIDIA · security_guardrail |
ai_security_and_guardrails |
colang_dialog_railstopic_injection_control | A1 · Apache-2.0 |
self_hosted, cloud_gpu |
| Guardrails AI Guardrails AI · security_guardrail |
ai_security_and_guardrails |
validator_hubstructured_output_enforcement | A1 · Apache-2.0 |
self_hosted, cpu_edge |
| Microsoft Presidio Microsoft · security_guardrail |
ai_security_and_guardrails |
pii_detection_anonymizationhipaa_gdpr_redaction | A1 · MIT |
cpu_edge, self_hosted |
| Lakera Guard Lakera · security_guardrail |
ai_security_and_guardrails |
prompt_injection_firewallindirect_rag_poisoning | A1 · Proprietary |
cloud_api, vpc |
| Prompt Security Prompt Security · security_guardrail |
ai_security_and_guardrails |
browser_api_dlpshadow_ai_governance | A1 · Proprietary |
cloud_api, vpc |
| Protect AI (LLM Guard & ModelScan) Protect AI · security_guardrail |
ai_security_and_guardrails |
model_pickle_supply_chainio_sanitization | A1 · MIT |
cpu_edge, self_hosted |
| Azure AI Content Safety Microsoft Azure · security_guardrail |
ai_security_and_guardrails |
prompt_shieldsgroundedness_check | A1 · Proprietary |
cloud_api |
| AWS Bedrock Guardrails AWS · security_guardrail |
ai_security_and_guardrails |
automated_reasoning_checkspii_topic_denials | A1 · Proprietary |
cloud_api |
| Meta Llama Guard 3 (8B / 1B) Meta · security_guardrail |
ai_security_and_guardrails |
mlcommons_hazard_taxonomytool_call_safety | A1 · Llama-3.2 |
cpu_edge, self_hosted |
| Giskard LLM & RAG Scanner Giskard · evaluation_harness |
ai_security_and_guardrails |
hallucination_sycophancy_scanci_security_probes | A1 · Apache-2.0 |
self_hosted |