docs: update listings for the july 2026 enrichment patch (#92)

Author: kimtth

README.md

@@ -142,6 +142,8 @@ Refereces: [DailyDoseOfDS - *Evolution of the Agent Landscape*](https://blog.dai
   - [Agent Research](section/best_practices.md#agent-research)
   - [**Agent Research** (Ranked by cite count >=100)](section/best_practices.md#agent-research-ranked-by-cite-count-100)
   - [Tool Use: LLM to Master APIs](section/best_practices.md#tool-use)
+- **Security**
+  - [Security and Governance](section/best_practices.md#security-and-governance)
 - **Reference**
   - [Proposals & Glossary](section/best_practices.md#proposals--glossary)
 

section/applications.md

@@ -236,7 +236,7 @@
  ![**github stars**](https://img.shields.io/github/stars/run-llama/llama_index?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Mastra](https://github.com/mastra-ai/mastra): TypeScript framework for building AI-powered applications and agents with workflows, RAG, integrations, and evals. blog:[Mastra Blog](https://mastra.ai/blog)
  ![**github stars**](https://img.shields.io/github/stars/mastra-ai/mastra?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
-- [Microsoft Agent Framework](https://github.com/microsoft/agent-framework): Unified Microsoft SDK for building agents from simple chats to complex graph-based multi-agent workflows. blog:[Agent framework](https://devblogs.microsoft.com/agent-framework/)
+- [Microsoft Agent Framework](https://github.com/microsoft/agent-framework):💡Unified Microsoft SDK for building agents from simple chats to complex graph-based multi-agent workflows. blog:[Agent framework](https://devblogs.microsoft.com/agent-framework/)
  ![**github stars**](https://img.shields.io/github/stars/microsoft/agent-framework?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Microsoft Semantic Kernel](https://github.com/microsoft/semantic-kernel):💡Plugin-based AI orchestration framework with strong .NET and Python support. blog:[Semantic kernel](https://devblogs.microsoft.com/semantic-kernel/) [Feb 2023]
  ![**github stars**](https://img.shields.io/github/stars/microsoft/semantic-kernel?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
@@ -466,11 +466,15 @@
 - [Hyperlight](https://github.com/hyperlight-dev/hyperlight): Embeddable micro-VM runtime for low-latency untrusted code execution. [Nov 2024] ![**github stars**](https://img.shields.io/github/stars/hyperlight-dev/hyperlight?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [KTransformers](https://github.com/kvcache-ai/ktransformers): A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations [Jul 2024] ![**github stars**](https://img.shields.io/github/stars/kvcache-ai/ktransformers?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [lemonade](https://github.com/lemonade-sdk/lemonade): Runtime for discovering and running local AI apps with optimized LLM serving on GPUs and NPUs. ![**github stars**](https://img.shields.io/github/stars/lemonade-sdk/lemonade?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [llama.cpp](https://github.com/ggml-org/llama.cpp):🏆Minimal-dependency C/C++ inference runtime for local and cloud LLMs, with GGUF quantization, wide hardware support, and an OpenAI-compatible server. [Mar 2023] ![**github stars**](https://img.shields.io/github/stars/ggml-org/llama.cpp?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [llamafile](https://github.com/mozilla-ai/llamafile):💡Distribute and run LLMs with a single file. [Sep 2023] ![**github stars**](https://img.shields.io/github/stars/mozilla-ai/llamafile?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [llmfit](https://github.com/AlexsJones/llmfit): Finds models and providers that run on your hardware. [Feb 2026] ![**github stars**](https://img.shields.io/github/stars/AlexsJones/llmfit?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [MLC LLM](https://github.com/mlc-ai/mlc-llm): Universal LLM deployment engine with ML compilation. [Apr 2023] ![**github stars**](https://img.shields.io/github/stars/mlc-ai/mlc-llm?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [MLX](https://github.com/ml-explore/mlx): Apple's array framework for efficient machine learning on Apple silicon, with examples for LLM inference, training, and LoRA fine-tuning. [2023] ![**github stars**](https://img.shields.io/github/stars/ml-explore/mlx?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [ollama](https://github.com/jmorganca/ollama):💡Run and serve local large language models from a simple CLI and local API. [Jun 2023]
+- [ONNX Runtime GenAI](https://github.com/microsoft/onnxruntime-genai):💡Cross-platform ONNX runtime for on-device generative AI, supporting model inference, token sampling, KV-cache management, constrained decoding, and tool-calling grammars. [2024] ![**github stars**](https://img.shields.io/github/stars/microsoft/onnxruntime-genai?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [SGLang](https://github.com/sgl-project/sglang):💡Programmable serving runtime for LLM and multimodal inference. [Jan 2024] ![**github stars**](https://img.shields.io/github/stars/sgl-project/sglang?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM): NVIDIA inference framework with optimized kernels, model-parallel serving, and advanced runtime features such as speculative decoding and prefill/decode disaggregation. [Oct 2023] ![**github stars**](https://img.shields.io/github/stars/NVIDIA/TensorRT-LLM?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [vLLM](https://github.com/vllm-project/vllm):🏆Easy-to-use library for LLM inference and serving. [Feb 2023]
 - [vllm-omni](https://github.com/vllm-project/vllm-omni): A framework for efficient model inference with omni-modality models [Sep 2025] ![**github stars**](https://img.shields.io/github/stars/vllm-project/vllm-omni?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [WebLLM](https://github.com/mlc-ai/web-llm): High-Performance In-Browser LLM Inference Engine. [Apr 2023] ![**github stars**](https://img.shields.io/github/stars/mlc-ai/web-llm?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
@@ -485,6 +489,7 @@
 - [keep](https://github.com/keephq/keep): The open-source AIOps and alert management platform [Feb 2023] ![**github stars**](https://img.shields.io/github/stars/keephq/keep?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [langfuse](https://github.com/langfuse/langfuse):💡Traces, evals, prompt management and metrics to debug and improve your LLM application. [May 2023]
 - [MLflow](https://github.com/mlflow/mlflow):🏆Open-source AI engineering platform for agents, LLMs, and ML models. [Jun 2018] ![**github stars**](https://img.shields.io/github/stars/mlflow/mlflow?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [OpenInference](https://github.com/Arize-ai/openinference): OpenTelemetry-compatible semantic conventions and instrumentation for tracing LLM calls, retrieval, tools, and agent workflows across common frameworks. [2023] ![**github stars**](https://img.shields.io/github/stars/Arize-ai/openinference?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Opik](https://github.com/comet-ml/opik): Debug, evaluate, and monitor LLM applications, RAG systems, and agentic workflows. [May 2023] ![**github stars**](https://img.shields.io/github/stars/comet-ml/opik?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [promptfoo](https://github.com/promptfoo/promptfoo):💡Test and evaluate prompts, agents, and RAG systems. [Apr 2023] ![**github stars**](https://img.shields.io/github/stars/promptfoo/promptfoo?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [TensorZero](https://github.com/tensorzero/tensorzero): LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation. [Jul 2024] ![**github stars**](https://img.shields.io/github/stars/tensorzero/tensorzero?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
@@ -613,6 +618,7 @@
 
 - [ACU - Awesome Agents for Computer Use](https://github.com/francedot/acu) ![**github stars**](https://img.shields.io/github/stars/francedot/acu?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Anthropic Claude's computer use](https://www.anthropic.com/news/developing-computer-use): [23 Oct 2024]
+- [BrowserGym](https://github.com/ServiceNow/BrowserGym): Framework for building and evaluating web agents with Gym-style environments; integrates WebArena, WorkArena, VisualWebArena, MiniWoB++, and other benchmarks. [2024] ![**github stars**](https://img.shields.io/github/stars/ServiceNow/BrowserGym?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Computer Agent Arena Leaderboard](https://arena.xlang.ai/leaderboard) [Apr 2025]
 - [Agent.exe](https://github.com/corbt/agent.exe): Electron app to use computer use APIs. [Oct 2024] ![**github stars**](https://img.shields.io/github/stars/corbt/agent.exe?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [CogAgent](https://github.com/THUDM/CogAgent): An open-sourced end-to-end VLM-based GUI Agent [Dec 2023] ![**github stars**](https://img.shields.io/github/stars/THUDM/CogAgent?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
@@ -757,7 +763,7 @@
 - [PR-Agent](https://github.com/Codium-ai/pr-agent): Efficient code review and handle pull requests, by providing AI feedbacks and suggestions [Jan 2023] ![**github stars**](https://img.shields.io/github/stars/Codium-ai/pr-agent?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [PySpur](https://github.com/PySpur-Dev/pyspur): Drag-and-Drop. an AI agent builder in Python. [Sep 2024] ![**github stars**](https://img.shields.io/github/stars/PySpur-Dev/pyspur?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Python-to-Rust Migration with Claude](https://www.infoworld.com/article/4135218/what-i-learned-using-claude-sonnet-to-migrate-python-to-rust.html): Lessons from using Claude on cross-language migrations. [2025]
-- [QueryWeaver](https://github.com/FalkorDB/QueryWeaver): An open-source Text2SQL tool that converts plain-English questions into SQL using graph-powered schema understanding. ![**github stars**](https://img.shields.io/github/stars/FalkorDB/QueryWeaver?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [QueryWeaver](https://github.com/FalkorDB/QueryWeaver): An open-source Text2SQL tool that converts plain-English questions into SQL using graph-powered schema. ![**github stars**](https://img.shields.io/github/stars/FalkorDB/QueryWeaver?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [ralph](https://github.com/snarktank/ralph): an autonomous AI agent loop that runs Amp repeatedly until all PRD items are complete. [Jan 2026] ![**github stars**](https://img.shields.io/github/stars/snarktank/ralph?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Replit Agent](https://replit.com/) [09 Sep 2024]
 - [Ruler](https://github.com/intellectronica/ruler): Centralise Your AI Coding Assistant Instructions [May 2025] ![**github stars**](https://img.shields.io/github/stars/intellectronica/ruler?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)

section/azure.md

@@ -85,13 +85,15 @@
 
 - [agent-governance-toolkit](https://github.com/microsoft/agent-governance-toolkit) - Policy enforcement, identity, and sandboxing for secure enterprise agents. (Mar 2026) ![**github stars**](https://img.shields.io/github/stars/microsoft/agent-governance-toolkit?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [AI Central](https://github.com/microsoft/AICentral) - Control plane for authenticated, resilient access to multiple OpenAI endpoints. (Oct 2023) ![**github stars**](https://img.shields.io/github/stars/microsoft/AICentral?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview) - 💡Managed text and image moderation service, with APIs for harmful-content analysis, groundedness detection, protected material, and custom categories.
 - [Azure AI Evaluation SDK](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/develop/evaluate-sdk) - 💡Evaluation tooling for generative AI quality and safety metrics. (Oct 2024)
 - [EvalsforAgentsInterop](https://github.com/microsoft/EvalsforAgentsInterop) - Evaluates LLM-powered productivity agents through realistic scenario simulations. (Nov 2025) ![**github stars**](https://img.shields.io/github/stars/microsoft/EvalsforAgentsInterop?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [MDASH](https://www.microsoft.com/en-us/security/blog/2026/05/12/defense-at-ai-speed-microsofts-new-multi-model-agentic-security-system-tops-leading-industry-benchmark/) - Multi-model agentic security harness for vulnerability discovery and proof. (May 2026)
 - [Microsoft Entra Agent ID](https://techcommunity.microsoft.com/blog/microsoft-entra-blog/announcing-microsoft-entra-agent-id-secure-and-manage-your-ai-agents/3827392) - Central registration and governance for organizational AI agents. (20 May 2025)
 - [Presidio](https://github.com/microsoft/presidio) - 🏆Context-aware, pluggable PII detection and de-identification for text and images. (Oct 2019) ![**github stars**](https://img.shields.io/github/stars/microsoft/presidio?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [Presidio Research](https://github.com/microsoft/presidio-research) - Data science tools for developing and evaluating Presidio PII recognizers. (Jan 2020) ![**github stars**](https://img.shields.io/github/stars/microsoft/presidio-research?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
 - [PyRIT](https://github.com/Azure/PyRIT) - 💡Risk identification toolkit targeting robustness, safety, and adversarial prompt detection. (Dec 2023) ![**github stars**](https://img.shields.io/github/stars/Azure/PyRIT?style=flat&label=%20&color=f0f1f2&cacheSeconds=360000)
+- [Prompt Shields](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection) - Azure AI Content Safety protection for direct user-prompt attacks and indirect prompt injection embedded in third-party documents.
 - [Securing MCP: A Control Plane for Agent Tool Execution](https://developer.microsoft.com/blog/securing-mcp-a-control-plane-for-agent-tool-execution) - Introduces Agent Governance Toolkit for MCP tool definition scanning, policy enforcement, response inspection, identity, and audit logs. [Apr 2026]
 
 ## Data Processing & Memory
@@ -199,6 +201,7 @@
 - [Assistants API](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-openai-service-announces-assistants-api-new-models-for/ba-p/4049940) - Code Interpreter, Function calling, Knowledge retrieval tool, and Threads. (06 Feb 2024)
 - [Azure AI Agent Service](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/introducing-azure-ai-agent-service/4298357) - 💡Managed agent service in Azure AI Foundry. (19 Nov 2024)
 - [Azure AI Content Understanding](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/announcing-azure-ai-content-understanding-transforming-multimodal-data-into-insi/4297196) - Transforming Multimodal Data into Insights.
+- [Azure AI Document Intelligence](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview) - 💡OCR and document-understanding service for extracting text, tables, structure, and key/value pairs, with prebuilt and custom models for intelligent document processing.
 - [Azure AI Foundry](https://ai.azure.com/) - 🏆Portal for building, evaluating, and managing AI applications and agents. (19 Nov 2024)
 - [Azure AI Foundry Agent Service](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/announcing-general-availability-of-azure-ai-foundry-agent-service/4414352) - Managed service for creating enterprise-grade, multi-agent systems. (20 May 2025)
 - [Azure AI Foundry Fine Tuning](https://techcommunity.microsoft.com/blog/aiplatformblog/what%E2%80%99s-new-in-azure-ai-foundry-fine-tuning/4413873) - Reinforcement Fine-Tuning (RFT) with o4-mini. (20 May 2025)
@@ -437,6 +440,7 @@
 - [AI Agent-Driven Auto Insurance Claims RAG Pipeline](https://techcommunity.microsoft.com/t5/azure-architecture-blog/exploring-ai-agent-driven-auto-insurance-claims-rag-pipeline/ba-p/4233779) - Agent-driven claims processing reference. (09 Sep 2024)
 - [AI decision tree](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/strategy) - Selecting the most suitable tools and platforms for your generative and nongenerative AI use cases.
 - [AI Feed](https://techcommunity.microsoft.com/t5/artificial-intelligence-and/ct-p/AI) - Azure AI news, events, and discussions.
+- [AI gateway capabilities in Azure API Management](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities) - 💡Secure, scale, observe, and govern models, agents, MCP servers, and A2A APIs with authentication, token controls, semantic caching, load balancing, and policy enforcement.
 - [AI gateway capabilities in Azure API Management](https://techcommunity.microsoft.com/blog/integrationsonazureblog/ai-gateway-enhancements-llm-policies-real-time-api-support-content-safety-and-mo/4409828) - Semantic Caching. Azure AI Content Safety. LLM policies (llm-token-limit, llm-emit-metric, llm-content-safety). (01 May 2025)
 - [AI Landing Zones Guardrails for Azure Machine Learning](https://www.azadvertizer.net/azpolicyinitiativesadvertizer/Enforce-Guardrails-MachineLearning.html) - Recommended Azure Policy initiative for Azure Machine Learning guardrails.
 - [AI Landing Zones Guardrails for Bot Service](https://www.azadvertizer.net/azpolicyinitiativesadvertizer/Enforce-Guardrails-BotService.html) - Recommended Azure Policy initiative for Bot Service guardrails.