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 |
|---|---|---|---|---|
| OpenAI GPT-5 OpenAI · model_family_version |
llm_frontier_cloud |
reasoningtool_callingmultimodal | B2 · Proprietary |
cloud_api |
| OpenAI o3 OpenAI · model_family_version |
llm_frontier_cloud |
deep_reasoningcode_verifiers | B2 · Proprietary |
cloud_api |
| Anthropic Claude Opus 4.6 Anthropic · model_family_version |
llm_frontier_cloud |
agentic_codinglong_horizontool_use | B2 · Proprietary |
cloud_api |
| Anthropic Claude Sonnet 4.6 Anthropic · model_family_version |
llm_frontier_cloud |
agentic_codingfast_tool_loop | B2 · Proprietary |
cloud_api |
| Google Gemini 2.5 Pro Google · model_family_version |
llm_frontier_cloud |
1m_contextmultimodalcode_synthesis | B2 · Proprietary |
cloud_api |
| Google Gemini 2.5 Flash Google · model_family_version |
llm_frontier_cloud |
low_latencyhybrid_tier1multimodal | B1 · Proprietary |
cloud_api |
| Mistral Large 2 Mistral AI · model_family_version |
llm_frontier_cloud |
multilingualfunction_calling | B2 · Mistral-Research |
cloud_api, self_hosted |
| Cohere Command A Cohere · model_family_version |
llm_frontier_cloud |
grounded_ragcitationsenterprise | B1 · Proprietary |
cloud_api, vpc |
| Meta Llama 4 Maverick Meta · model_family_version |
llm_open_weights_cloud |
moe_open_weightsmultimodaltool_calling | B2 · Llama-4 |
cloud_api, self_hosted |
| Meta Llama 3.3 70B Instruct Meta · model_family_version |
llm_open_weights_cloud |
open_weightsinstruction_following | B2 · Llama-3.3 |
cloud_api, self_hosted |
| GLM-5.3-Flash (Ollama Cloud) Zhipu / Ollama Cloud · model_family_version |
llm_open_weights_cloud |
hybrid_tier1fast_jsonqueue_worker | A2 · Apache-2.0 |
cloud_api |
| Muse-Spark-Open (Ollama Cloud) Meta / Ollama Cloud · model_family_version |
llm_open_weights_cloud |
swarm_workerbilateral_speech_actscode | A2 · Apache-2.0 |
cloud_api |
| DeepSeek-R1 DeepSeek · model_family_version |
llm_open_weights_cloud |
chain_of_thoughtmath_verifiers | B2 · MIT |
cloud_api, self_hosted |
| Qwen3-235B-A22B Alibaba Qwen · model_family_version |
llm_open_weights_cloud |
moe_open_weightscodingmultilingual | B2 · Apache-2.0 |
cloud_api, self_hosted |
| Ollama Cloud Inference Service Ollama · inference_runtime |
llm_open_weights_cloud |
cloud_inference_apiopenai_compatible | A2 · MIT |
cloud_api |
| vLLM PagedAttention Engine vLLM Project · inference_runtime |
llm_open_weights_cloud |
continuous_batchingprefix_cachingtensor_parallel | B1 · Apache-2.0 |
self_hosted, cloud_gpu |
| Hugging Face Hub & TGI Hugging Face · model_repository |
llm_open_weights_cloud |
safetensors_registrymodel_cardstgi_serving | A2 · Apache-2.0 |
cloud_api, self_hosted |
| Phi-4-mini-instruct (Q4_K_M) Microsoft · model_family_version |
slm_cpu_edge_quantized |
cpu_inferencefunction_callingcompact_reasoning | A1 · MIT |
cpu_edge, cloud_api |
| Qwen3-Coder-7B-Instruct (GGUF) Alibaba Qwen · model_family_version |
slm_cpu_edge_quantized |
cpu_inferencecode_repairast_patching | A1 · Apache-2.0 |
cpu_edge, self_hosted |
| Meta Llama 3.2 3B Instruct (Q4) Meta · model_family_version |
slm_cpu_edge_quantized |
cpu_inferencescent_scoringrouter_tier1 | A1 · Llama-3.2 |
cpu_edge, mobile |
| Google Gemma 3 4B IT (Q4) Google · model_family_version |
slm_cpu_edge_quantized |
cpu_inferencevision_edgemultilingual | A1 · Gemma |
cpu_edge, self_hosted |
| BitNet b1.58 2B4T Microsoft Research · model_family_version |
slm_cpu_edge_quantized |
ternary_1_58bitultra_low_energy_cpu | A1 · MIT |
cpu_edge |
| SmolLM2-1.7B-Instruct Hugging Face · model_family_version |
slm_cpu_edge_quantized |
cpu_inferenceon_device_classifier | A1 · Apache-2.0 |
cpu_edge, browser_wasm |
| llama.cpp (GGML / AVX-512 / NEON) ggml-org · inference_runtime |
slm_cpu_edge_quantized |
cpu_simd_runtimegguf_quantizationgrammar_json | A1 · MIT |
cpu_edge, self_hosted |
| Intel OpenVINO GenAI Intel · inference_runtime |
slm_cpu_edge_quantized |
int4_cpu_npuxeon_amx | A1 · Apache-2.0 |
cpu_edge, self_hosted |
| ONNX Runtime GenAI Microsoft · inference_runtime |
slm_cpu_edge_quantized |
cross_platform_cpudirectml_npu | A1 · MIT |
cpu_edge, mobile |
| FLUX.1-dev Black Forest Labs · model_family_version |
multimodal_vision_audio_3d |
image_generationprompt_adherencetypography | B1 · FLUX-NonCommercial |
cloud_api, self_hosted |
| FLUX.1-schnell Black Forest Labs · model_family_version |
multimodal_vision_audio_3d |
4step_image_genpermissive_commercial | A2 · Apache-2.0 |
cloud_api, self_hosted |
| Stable Diffusion 3.5 Large Stability AI · model_family_version |
multimodal_vision_audio_3d |
image_generationcontrolnet_lora | B1 · Stability-Community |
cloud_api, self_hosted |
| Meta SAM 2.1 Meta · model_family_version |
multimodal_vision_audio_3d |
video_image_segmentationzero_shot_mask | A1 · Apache-2.0 |
self_hosted, cloud_gpu |
| Whisper Large v3 Turbo OpenAI · model_family_version |
multimodal_vision_audio_3d |
speech_to_textmultilingual_asr | A1 · MIT |
cloud_api, cpu_edge, self_hosted |
| IBM Docling IBM · rag_component |
multimodal_vision_audio_3d |
pdf_layout_parsingtable_ocringestion | A1 · MIT |
cpu_edge, self_hosted |
| Microsoft TRELLIS 3D Microsoft · model_family_version |
multimodal_vision_audio_3d |
3d_gltf_mesh_genstructured_latents | B1 · MIT |
cloud_gpu, self_hosted |
| Tencent Hunyuan3D-2 Tencent · model_family_version |
multimodal_vision_audio_3d |
3d_shape_texture_genpbr_materials | B1 · Hunyuan-Community |
cloud_gpu, self_hosted |
| Amazon Chronos-Bolt (Base) AWS / Amazon Science · model_family_version |
timeseries_foundation_models |
zero_shot_forecastingquantile_crpscpu_fast | A1 · Apache-2.0 |
cpu_edge, self_hosted, cloud_api |
| Google TimesFM 2.0 (500M) Google Research · model_family_version |
timeseries_foundation_models |
zero_shot_forecastinglong_horizoncovariates | A1 · Apache-2.0 |
cpu_edge, self_hosted, cloud_gpu |
| Salesforce Moirai-MoE Salesforce AI Research · model_family_version |
timeseries_foundation_models |
multivariate_any_variateprobabilistic_crps | A1 · Apache-2.0 |
self_hosted, cloud_gpu |
| Lag-Llama Morgan Stanley / ServiceNow · model_family_version |
timeseries_foundation_models |
probabilistic_univariatestudent_t_head | A1 · Apache-2.0 |
cpu_edge, self_hosted |
| Nixtla TimeGPT-1 Nixtla · model_family_version |
timeseries_foundation_models |
hosted_forecasting_apianomaly_detectionexogenous | B1 · Proprietary |
cloud_api |
| PatchTST IBM / Princeton · model_family_version |
timeseries_foundation_models |
channel_independent_patchessupervised_baseline | A1 · Apache-2.0 |
cpu_edge, self_hosted |
| Datadog Toto (Open Weights) Datadog · model_family_version |
timeseries_foundation_models |
observability_metrics_tsregime_shift_anomaly | A1 · Apache-2.0 |
self_hosted, cloud_gpu |
| Sundial Time-Series Flow THUML · model_family_version |
timeseries_foundation_models |
flow_matching_probabilisticnon_gaussian_tails | A1 · Apache-2.0 |
self_hosted, cloud_gpu |