Highest Evidence AI Agents

Agents with the strongest public evidence depth, weighted toward A/B grades and high HVTrust. Updated from the same generated registry data as the leaderboard, so the list changes with every cron refresh.

16Agents in slice
92Average HVTrust
5Updated in last 14 days

Trust Shape

Safety82%Identity100%Transparency83%Maintenance97%Adoption93%

Activity Signals

Popularity43%Commit Activity87%Freshness31%Scorecard67%Signed Commits93%
AgentCategoryGradeRankHVTrustFresh
Haystackdeepset-ai/haystack Agent Frameworks A #1 96.8 1d
Vercel AI SDKvercel/ai Agent Frameworks A #2 96.4 today
Codexopenai/codex Coding Agents A #3 93.8 today
LangGraphlangchain-ai/langgraph Agent Frameworks A #4 92.9 today
Trigger.devtriggerdotdev/trigger.dev Workflow Platforms A #5 91.9 1d
LiveKit Agentslivekit/agents Voice & Conversational A #6 91.8 1d
Clinecline/cline Coding Agents A #7 91.7 today
Codebase Memory MCPDeusData/codebase-memory-mcp MCP Servers A #8 91.6 today
Strands Agentsstrands-agents/harness-sdk Agent Frameworks A #9 91.5 today
Qwen CodeQwenLM/qwen-code Coding Agents A #10 90.9 today
MCP Inspectormodelcontextprotocol/inspector Protocols & Tool Integration A #11 90.0 today
n8nn8n-io/n8n Workflow Platforms A #12 89.8 today
MLflowmlflow/mlflow Observability & Evaluation A #13 89.8 today
LeRobothuggingface/lerobot Robotics & Embodied A #14 89.7 today
A2A / Agent2Agent Protocola2aproject/A2A Protocols & Tool Integration A #15 89.5 1d
Playwright MCPmicrosoft/playwright-mcp MCP Servers A #16 89.5 2d

Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology