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.
| Agent | Category | Grade | Rank | HVTrust | Fresh |
|---|---|---|---|---|---|
| Vercel AI SDKvercel/ai | Agent Frameworks | A | #1 | 95.1 | today |
| Haystackdeepset-ai/haystack | Agent Frameworks | A | #2 | 93.9 | 2d |
| Codexopenai/codex | Coding Agents | A | #3 | 93.2 | today |
| Strands Agentsstrands-agents/harness-sdk | Agent Frameworks | A | #4 | 91.6 | 1d |
| n8nn8n-io/n8n | Workflow Platforms | A | #5 | 91.3 | today |
| Qwen CodeQwenLM/qwen-code | Coding Agents | A | #6 | 90.8 | today |
| Codebase Memory MCPDeusData/codebase-memory-mcp | MCP Servers | A | #7 | 90.5 | today |
| Trigger.devtriggerdotdev/trigger.dev | Workflow Platforms | A | #8 | 90.5 | 1d |
| Clinecline/cline | Coding Agents | A | #9 | 90.2 | today |
| Playwright MCPmicrosoft/playwright-mcp | MCP Servers | A | #10 | 89.7 | 4d |
| MCP Inspectormodelcontextprotocol/inspector | Protocols & Tool Integration | A | #11 | 89.1 | today |
| Browser Harnessbrowser-use/browser-harness | Browser & Computer Use | A | #12 | 89.0 | today |
| A2A / Agent2Agent Protocola2aproject/A2A | Protocols & Tool Integration | A | #13 | 88.7 | 2d |
| LiveKit Agentslivekit/agents | Voice & Conversational | A | #14 | 88.7 | 1d |
| Cloudflare Agentscloudflare/agents | Agent Frameworks | A | #15 | 88.7 | 2d |
| OpenAI Agents SDK (JS)openai/openai-agents-js | Agent Frameworks | A | #16 | 88.6 | today |