Blog / Weekly trust snapshot

AI Agent Trust Snapshot — Week 25, 2026

June 21, 2026 · registry snapshot 2026-06-14 → 2026-06-21 · 300 agents tracked

Every week HVTracker diffs its registry snapshots and publishes what actually changed: trust-score moves of 3+ points, new listings, and gained provenance or MCP support. This edition compares the 2026-06-14 and 2026-06-21 snapshots — 24 gains, 18 declines, 78 new listings, 0 provenance and 1 MCP additions. Every figure below is generated directly from those snapshots.

Trust score up (24)

AgentHVTrustChange
ASM 22.8 → 59.4 +36.6
TEN Framework 24.0 → 60.3 +36.3
Obsidian Second Brain 23.9 → 60.0 +36.1
Engram 24.9 → 60.4 +35.5
Hivemind 23.9 → 57.1 +33.2
TencentDB Agent Memory 24.0 → 56.1 +32.1
Turbovec 24.4 → 56.1 +31.7
PraisonAI 38.1 → 67.2 +29.1
AI Town 21.4 → 49.9 +28.5
SWE-agent 37.9 → 66.1 +28.2
HyperAgent 19.6 → 46.7 +27.1
Burr 38.6 → 65.1 +26.5
Griptape 38.0 → 64.4 +26.4
ClawWork 17.6 → 41.8 +24.2
OpenHands 51.2 → 71.6 +20.4
Roo Code 35.4 → 54.7 +19.3
Marvin 36.3 → 54.8 +18.5
Aider 39.0 → 56.3 +17.3
MetaGPT 30.2 → 44.6 +14.4
Superpowers 59.6 → 67.7 +8.1
Guardrails AI 80.2 → 86.8 +6.6
Semantic Kernel 67.1 → 71.6 +4.5
pgvector 52.8 → 56.9 +4.1
Open Interpreter 68.7 → 72.4 +3.7

Trust score down (18)

AgentHVTrustChange
CopilotKit 76.7 → 45.7 -31.0
Bernstein 81.4 → 75.8 -5.6
BrowserGym agents 57.7 → 52.2 -5.5
PydanticAI 90.2 → 85.1 -5.1
Skyvern 88.5 → 83.4 -5.1
agentmemory 71.0 → 65.9 -5.1
Promptfoo 76.8 → 71.8 -5.0
Qdrant 74.5 → 69.5 -5.0
OpenClaw 88.7 → 84.2 -4.5
OpenAI Agents SDK 88.9 → 84.5 -4.4
Swarm by OpenAI 52.1 → 47.9 -4.2
Quivr 45.9 → 41.8 -4.1
AutoGPT 69.6 → 65.9 -3.7
LlamaIndex 46.0 → 42.3 -3.7
Rasa 60.7 → 57.1 -3.6
Sotopia agents 51.3 → 47.8 -3.5
Agent-S 49.9 → 46.7 -3.2
Qwen Agent 51.2 → 48.1 -3.1

Newly listed (78)

AgentCategoryHVTrust
Hindsight Memory & Knowledge85.2
Threadplane Agent Frameworks82.2
MCP Python SDK Protocols & Tool Integration70.1
Zvec Memory & Knowledge68.7
AG2 Agent Frameworks68.1
Context7 Protocols & Tool Integration66.8
Microsoft MCP Catalog Protocols & Tool Integration66.8
MCP TypeScript SDK Protocols & Tool Integration66.2
mcp-use Protocols & Tool Integration63.6
Ponytail Coding Agents62.5
Eve Needs review61.5
Serena Protocols & Tool Integration60.8
Jido Agent Frameworks60.3
Agent Reach Protocols & Tool Integration58.8
Lumibot Research & Data56.3
Habitat-Lab Robotics & Embodied52.6
autoMate Browser & Computer Use48.1
YoMo Agent Frameworks45.7
Srcbook UI & App Builders45.6
Chat Nio LLM Gateways & Infra43.3
Open Deep Research (dzhng) Research & Data42.7
Youtu-Agent Agent Frameworks41.3
MCP Playwright Protocols & Tool Integration36.2
ScaleCUA Browser & Computer Use33.6
PyWinAssistant Browser & Computer Use29.5
Dyad UI & App Builders27.2
AstrBot Voice & Conversational26.9
Chrome DevTools MCP Protocols & Tool Integration26.9
MCP Specification Protocols & Tool Integration26.8
Hatchet Workflow Platforms26.8
ToolJet UI & App Builders26.7
Omnigent Agent Frameworks26.5
Open Multi-Agent Multi-Agent Systems26.2
GitHub MCP Server Protocols & Tool Integration26.0
Conductor Workflow Platforms26.0
DeepSeek-Reasonix Coding Agents25.6
n8n-MCP Protocols & Tool Integration25.6
Figma Context MCP Protocols & Tool Integration25.4
LazyLLM Agent Frameworks25.4
OpenLIT Observability & Evaluation25.4
Golem Workflow Platforms24.6
fast-agent Agent Frameworks24.4
OpenBB Research & Data24.2
Steel Browser Browser & Computer Use24.0
IntentKit Agent Frameworks23.8
MCP Go Protocols & Tool Integration23.6
Agently Agent Frameworks23.2
Stakpak Agent Coding Agents22.9
Agentic Security Security & Guardrails22.7
BotSharp Agent Frameworks22.7
Yao UI & App Builders22.4
Agent Squad Multi-Agent Systems22.3
HumanLayer Coding Agents22.1
LLM Wiki Agent Memory & Knowledge22.0
Upsonic Agent Frameworks21.9
PentestAgent Security & Guardrails21.8
LiteFlow Workflow Platforms21.7
Mirascope Agent Frameworks21.7
Kodu Coding Agents21.7
ByteRover CLI Memory & Knowledge21.5
FinRobot Research & Data21.0
Parlant Agent Frameworks20.9
TuriX Browser & Computer Use20.6
Call Center AI Voice & Conversational20.6
Convex Chef UI & App Builders20.5
MiroThinker Research & Data19.7
agentUniverse Agent Frameworks19.1
HexStrike AI Security & Guardrails18.7
PocketFlow Agent Frameworks18.6
Tongyi DeepResearch Research & Data18.5
DeepResearchAgent Multi-Agent Systems18.4
Magentic Agent Frameworks18.2
OpenAI CUA Sample App Browser & Computer Use18.0
OpenBrowser Browser & Computer Use17.8
AgentBench Observability & Evaluation16.7
ChatArena Multi-Agent Systems16.0
Nanobrowser Browser & Computer Use15.3
AutoAgent Agent Frameworks15.3

MCP support gained (1)

AgentCategoryStatus
Vellum Assistant Memory & Knowledgedeclared
Generated automatically from the 2026-06-14 and 2026-06-21 registry snapshots — no numbers in this post are estimated or written by hand. Method: HVTrust methodology · live diff: what changed this week · feed: RSS.