guard0-ai · JBAhire · Jun 10, 2026 · Jun 10, 2026
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](http://makeapullrequest.com)
-[![Evaluations](https://img.shields.io/badge/Evaluations-106-blue.svg)](#-current-coverage)
+[![Evaluations](https://img.shields.io/badge/Evaluations-156-blue.svg)](#-current-coverage)
 [![GitHub Stars](https://img.shields.io/github/stars/Guard0-Security/TrustVector?style=social)](https://github.com/Guard0-Security/TrustVector)
 
 TrustVector is an evidence-based evaluation framework for AI systems, providing transparent, multi-dimensional trust scores across **security**, **privacy**, **performance**, **trust**, and **operational excellence**.
@@ -87,57 +87,54 @@ const customScore = calculateCustomScore(claudeSonnet, {
 
 ## 📊 Current Coverage
 
-**106 Total Evaluations** across 3 categories:
+**156 Total Evaluations** across 3 categories (last refreshed June 2026):
 
-### AI Models (38)
+### AI Models (60)
 
 **Frontier Models:**
-- ✅ Claude Sonnet 4.5, Claude Opus 4.1, Claude 3.7 Sonnet, Claude 3.5 Haiku (Anthropic)
-- ✅ GPT-5, GPT-4.5, GPT-4.1, GPT-4o, GPT-4o Mini (OpenAI)
-- ✅ o1, o1 Mini, o3, o3 Mini (OpenAI Reasoning)
-- ✅ Gemini 2.5 Pro, Gemini 2.0 Flash (Google)
-- ✅ Llama 4 Behemoth, Llama 4 Maverick, Llama 4 Scout, Llama 3.3 70B, Llama 3.1 405B (Meta)
-- ✅ Grok 3 Beta (xAI)
-- ✅ DeepSeek R1, DeepSeek V3 (DeepSeek)
-
-**Specialized & Open Source:**
-- ✅ Gemma 3 27B (Google)
-- ✅ Qwen2.5-VL 32B (Alibaba)
-- ✅ Nemotron Ultra 253B (NVIDIA)
-- ✅ Nova Pro (Amazon)
+- ✅ Claude Fable 5, Claude Opus 4.8 / 4.7 / 4.6 / 4.5, Claude Sonnet 4.6 / 4.5, Claude Haiku 4.5 (Anthropic)
+- ✅ GPT-5.5, GPT-5.4, GPT-5.3-Codex, GPT-5.2, GPT-5.1, GPT-5, o-series (OpenAI)
+- ✅ Gemini 3.1 Pro, Gemini 3.5 Flash, Gemini 3 Pro/Flash (Google)
+- ✅ Grok 4.3, Grok 4.1 (xAI)
+- ✅ Nova 2 Lite, Nova Pro (Amazon)
+
+**Open-Weight Models:**
+- ✅ DeepSeek V4, DeepSeek V3.2, DeepSeek R1 (DeepSeek)
+- ✅ Qwen3.5 (Alibaba), Kimi K2.6 (Moonshot), GLM-5 (Z.ai), MiniMax-M2
+- ✅ Mistral Large 3 (Mistral), Command A+ (Cohere)
+- ✅ Gemma 4, Gemma 3 (Google), gpt-oss-120b/20b (OpenAI)
+- ✅ Llama 4 Maverick/Scout, Llama 3.x (Meta), Nemotron (NVIDIA)
 
 **[See all models →](/data/models)**
 
-### AI Agents (34)
+### AI Agents (50)
 
-**Enterprise Platforms:**
-- ✅ Amazon Bedrock Agents, Azure Bot Service, Google Agent Builder
-- ✅ IBM Watson Assistant, Google Dialogflow, Amazon Lex
+**Coding & Autonomous Agents:**
+- ✅ Claude Code + Claude Agent SDK (Anthropic), OpenAI Codex, Devin (Cognition)
+- ✅ Cursor, GitHub Copilot coding agent, Google Jules, Gemini CLI, Manus
 
 **Developer Frameworks:**
-- ✅ LangGraph Agent, LlamaIndex Agent, CrewAI, AutoGen
-- ✅ Haystack, LangFlow, Flowise, E2B Agents
+- ✅ OpenAI Agents SDK, Google ADK, Microsoft Agent Framework, AWS Strands Agents
+- ✅ LangGraph, CrewAI, LlamaIndex, Pydantic AI, smolagents, Mastra, Dify
 
-**Autonomous Agents:**
-- ✅ AutoGPT, BabyAGI, AgentGPT, Adala
-- ✅ And 15+ more...
+**Enterprise Platforms:**
+- ✅ Amazon Bedrock Agents, Azure Bot Service, Gemini Enterprise Agent Platform
+- ✅ IBM watsonx Assistant, Google Dialogflow, Amazon Lex, and more
 
 **[See all agents →](/data/agents)**
 
-### MCP Servers (34)
-
-**Cloud & Infrastructure:**
-- ✅ AWS, Azure, Cloudflare, Docker, Kubernetes
+### MCP Servers (46)
 
-**Development Tools:**
-- ✅ GitHub, Git, Filesystem, Memory
+**Top Ecosystem Servers:**
+- ✅ Context7, Chrome DevTools MCP, Playwright MCP, Serena
 
-**Productivity & Business:**
-- ✅ Gmail, Google Drive, Calendar, Linear, Atlassian
-- ✅ Datadog, Elasticsearch, MongoDB
+**Official Vendor Servers:**
+- ✅ GitHub, Figma, Stripe, Notion, Vercel, Hugging Face, Zapier, Apify
 
-**Utilities:**
-- ✅ Brave Search, Fetch, Everything
+**Reference & Community:**
+- ✅ Fetch, Git, Filesystem, Memory, Sequential Thinking, Time, Everything
+- ✅ AWS, Azure, Cloudflare, Docker, Kubernetes, databases, and more
+- ⚠️ Archived reference servers (Puppeteer, Postgres, SQLite, Slack, …) are flagged with security advisories
 - ✅ And 15+ more...
 
 **[See all MCPs →](/data/mcps)**

diff --git a/data/agents/agentgpt.json b/data/agents/agentgpt.json
@@ -4,9 +4,9 @@
   "name": "AgentGPT",
   "provider": "Reworkd",
   "version": "Platform",
-  "last_evaluated": "2025-11-09",
+  "last_evaluated": "2026-06-10",
   "evaluated_by": "TrustVector Team",
-  "description": "Browser-based autonomous AI agent platform for deploying and managing GPT-powered agents. Enables users to create goal-oriented autonomous agents that break down objectives and execute tasks without continuous human intervention.",
+  "description": "DISCONTINUED: the AgentGPT repository was archived on 2026-01-28 (last release v1.0.0, Nov 2023) and the hosted site is frozen. Formerly a browser-based autonomous AI agent platform that let users create goal-oriented agents which break down objectives and execute tasks without continuous human intervention. Not recommended for new use.",
   "website": "https://agentgpt.reworkd.ai/",
   "trust_vector": {
     "performance_reliability": {
@@ -249,7 +249,7 @@
       }
     },
     "trust_transparency": {
-      "overall_score": 79,
+      "overall_score": 76,
       "criteria": {
         "documentation_quality": {
           "score": 75,
@@ -308,23 +308,30 @@
           "last_verified": "2025-11-09"
         },
         "community_support": {
-          "score": 73,
-          "confidence": "medium",
+          "score": 55,
+          "confidence": "high",
           "evidence": [
             {
               "source": "Community",
               "url": "https://github.com/reworkd/AgentGPT/discussions",
               "date": "2024-10-15",
               "value": "Active GitHub community and Discord"
+            },
+            {
+              "source": "GitHub Repository Status",
+              "url": "https://github.com/reworkd/AgentGPT",
+              "date": "2026-06-10",
+              "value": "Repository archived 2026-01-28; community activity has ceased"
             }
           ],
           "methodology": "Community engagement analysis",
-          "last_verified": "2025-11-09"
+          "last_verified": "2026-06-10",
+          "notes": "Score reduced: repository archived, no further community development"
         }
       }
     },
     "operational_excellence": {
-      "overall_score": 70,
+      "overall_score": 65,
       "criteria": {
         "ease_of_use": {
           "score": 88,
@@ -383,18 +390,25 @@
           "last_verified": "2025-11-09"
         },
         "production_readiness": {
-          "score": 60,
-          "confidence": "medium",
+          "score": 40,
+          "confidence": "high",
           "evidence": [
             {
               "source": "Platform Maturity",
               "url": "https://github.com/reworkd/AgentGPT",
               "date": "2024-10-01",
               "value": "Experimental platform, not designed for production use"
+            },
+            {
+              "source": "GitHub Repository Status",
+              "url": "https://github.com/reworkd/AgentGPT",
+              "date": "2026-06-10",
+              "value": "Repository archived 2026-01-28; last release v1.0.0 (Nov 2023); hosted site frozen"
             }
           ],
           "methodology": "Production readiness assessment",
-          "last_verified": "2025-11-09"
+          "last_verified": "2026-06-10",
+          "notes": "Score reduced: project discontinued and repository archived on 2026-01-28"
         },
         "reliability": {
           "score": 62,
@@ -474,7 +488,8 @@
     "Limited tool access and action capabilities",
     "Can be expensive with unpredictable OpenAI API costs",
     "No enterprise features (auth, monitoring, management)",
-    "Reliability and success rate varies significantly"
+    "Reliability and success rate varies significantly",
+    "Discontinued: repository archived 2026-01-28, hosted site frozen, no further updates"
   ],
   "metadata": {
     "license": "GPL-3.0",
@@ -500,6 +515,7 @@
   },
   "tags": [
     "autonomous",
-    "web-based"
+    "web-based",
+    "archived"
   ]
 }
diff --git a/data/agents/amazon-bedrock-agents.json b/data/agents/amazon-bedrock-agents.json
@@ -4,9 +4,9 @@
   "name": "Amazon Bedrock Agents",
   "provider": "Amazon Web Services",
   "version": "2024",
-  "last_evaluated": "2025-11-09",
+  "last_evaluated": "2026-06-10",
   "evaluated_by": "TrustVector Team",
-  "description": "Fully managed AWS service for building and deploying generative AI agents. Handles orchestration, memory, knowledge bases, and action groups with enterprise security and scalability built-in.",
+  "description": "Fully managed AWS service for building and deploying generative AI agents with orchestration, memory, knowledge bases, and action groups. Note: AWS's strategic agent runtime is now Bedrock AgentCore (GA 2025-10-13; framework-agnostic, 8-hour sessions, session isolation) paired with the open-source Strands Agents SDK; evaluate AgentCore for new builds.",
   "website": "https://aws.amazon.com/bedrock/agents/",
   "trust_vector": {
     "performance_reliability": {
@@ -378,10 +378,16 @@
               "url": "https://aws.amazon.com/bedrock/customers/",
               "date": "2024-10-01",
               "value": "Production-ready managed service with enterprise customers"
+            },
+            {
+              "source": "Amazon Bedrock AgentCore GA Announcement",
+              "url": "https://aws.amazon.com/about-aws/whats-new/2025/10/amazon-bedrock-agentcore-available/",
+              "date": "2026-06-10",
+              "value": "AWS's strategic agent runtime is now Bedrock AgentCore (GA 2025-10-13): framework-agnostic, 8-hour sessions, session isolation; complemented by the open-source Strands Agents SDK"
             }
           ],
           "methodology": "Production readiness assessment",
-          "last_verified": "2025-11-09"
+          "last_verified": "2026-06-10"
         }
       }
     }
@@ -448,7 +454,8 @@
     "Limited to AWS Bedrock foundation models",
     "Less flexibility than code-based frameworks",
     "Requires AWS expertise for optimal configuration",
-    "Not open source, limited customization of core orchestration"
+    "Not open source, limited customization of core orchestration",
+    "AWS's strategic focus has shifted to Bedrock AgentCore (GA 2025-10-13) and the Strands Agents SDK; new agent workloads should evaluate AgentCore first"
   ],
   "metadata": {
     "license": "Proprietary (AWS)",
@@ -471,6 +478,9 @@
     "regions_available": "Multiple AWS regions",
     "sla": "99.9%"
   },
+  "related_entities": [
+    "strands-agents"
+  ],
   "tags": [
     "aws"
   ]

diff --git a/data/agents/autogen.json b/data/agents/autogen.json
@@ -4,9 +4,9 @@
   "name": "Microsoft AutoGen",
   "provider": "Microsoft Research",
   "version": "0.4",
-  "last_evaluated": "2025-11-09",
+  "last_evaluated": "2026-06-10",
   "evaluated_by": "TrustVector Team",
-  "description": "Multi-agent conversation framework enabling next-gen LLM applications with conversable agents that can operate in various modes combining LLMs, human inputs, and tools. Supports complex workflows through agent conversations.",
+  "description": "MAINTENANCE MODE: AutoGen now receives bug/security fixes only and is superseded by the Microsoft Agent Framework (1.0 GA on 2026-04-03), the recommended migration path. AutoGen is a multi-agent conversation framework for LLM applications with conversable agents combining LLMs, human input, and tools across complex workflows.",
   "website": "https://microsoft.github.io/autogen/",
   "trust_vector": {
     "performance_reliability": {
@@ -377,10 +377,16 @@
               "url": "https://github.com/microsoft/autogen",
               "date": "2024-10-20",
               "value": "Very active community with Microsoft backing"
+            },
+            {
+              "source": "Microsoft Agent Framework Migration Guidance",
+              "url": "https://devblogs.microsoft.com/semantic-kernel/migrate-your-semantic-kernel-and-autogen-projects-to-microsoft-agent-framework-release-candidate/",
+              "date": "2026-06-10",
+              "value": "AutoGen is in maintenance mode (bug/security fixes only); Microsoft Agent Framework 1.0 reached GA on 2026-04-03 as the successor"
             }
           ],
           "methodology": "Community activity analysis",
-          "last_verified": "2025-11-09"
+          "last_verified": "2026-06-10"
         }
       }
     }
@@ -447,7 +453,8 @@
     "Requires careful prompt engineering for agent roles",
     "Limited built-in persistence for long-running workflows",
     "Some learning curve for advanced features",
-    "Performance depends heavily on LLM quality"
+    "Performance depends heavily on LLM quality",
+    "Maintenance mode: bug/security fixes only; new development targets Microsoft Agent Framework"
   ],
   "metadata": {
     "license": "Apache 2.0",
@@ -474,9 +481,13 @@
     "contributors": "559+",
     "transition_notice": "Microsoft Agent Framework is the recommended path forward; AutoGen receives maintenance and critical patches only"
   },
+  "related_entities": [
+    "microsoft-agent-framework"
+  ],
   "tags": [
     "multi-agent",
     "microsoft",
-    "open-source"
+    "open-source",
+    "maintenance-mode"
   ]
 }
diff --git a/data/agents/babyagi.json b/data/agents/babyagi.json
@@ -4,9 +4,9 @@
   "name": "BabyAGI",
   "provider": "Yohei Nakajima",
   "version": "Classic",
-  "last_evaluated": "2025-11-09",
+  "last_evaluated": "2026-06-10",
   "evaluated_by": "TrustVector Team",
-  "description": "Minimalist autonomous task-driven AI agent that creates, prioritizes, and executes tasks based on results of previous tasks and a predefined objective. Demonstrates AGI concepts in under 200 lines of code.",
+  "description": "ARCHIVED: the original BabyAGI repo was archived to babyagi_archive in September 2024 and replaced by an experimental self-building framework; it is not production-maintained. Originally a minimalist autonomous task-driven AI agent that created, prioritized, and executed tasks toward an objective, demonstrating AGI concepts in under 200 lines of code.",
   "website": "https://github.com/yoheinakajima/babyagi",
   "trust_vector": {
     "performance_reliability": {
@@ -310,7 +310,7 @@
       }
     },
     "operational_excellence": {
-      "overall_score": 61,
+      "overall_score": 57,
       "criteria": {
         "ease_of_integration": {
           "score": 75,
@@ -370,18 +370,25 @@
           "last_verified": "2025-11-09"
         },
         "production_readiness": {
-          "score": 50,
+          "score": 35,
           "confidence": "high",
           "evidence": [
             {
               "source": "Project Purpose",
               "url": "https://github.com/yoheinakajima/babyagi",
               "date": "2024-09-01",
               "value": "Designed as concept demonstration, not production system"
+            },
+            {
+              "source": "GitHub Repository Status",
+              "url": "https://github.com/yoheinakajima/babyagi",
+              "date": "2026-06-10",
+              "value": "Original repo archived to babyagi_archive (Sept 2024); replaced by an experimental self-building framework; not production-maintained"
             }
           ],
           "methodology": "Production readiness assessment",
-          "last_verified": "2025-11-09"
+          "last_verified": "2026-06-10",
+          "notes": "Score reduced: original project archived and unmaintained since September 2024"
         }
       }
     }
@@ -400,7 +407,8 @@
     "Can generate excessive tasks leading to high costs",
     "No built-in security or sandboxing features",
     "Limited tool integration in classic version",
-    "Unpredictable behavior and task completion quality"
+    "Unpredictable behavior and task completion quality",
+    "Archived (Sept 2024): original repo moved to babyagi_archive with no further maintenance"
   ],
   "metadata": {
     "license": "MIT",
@@ -471,6 +479,7 @@
   "tags": [
     "autonomous",
     "experimental",
-    "open-source"
+    "open-source",
+    "archived"
   ]
 }