Agent-native E2E runtime with verifiable safety. 16 MCP tools including alethia_propose_tests (agent generates tests from a URL), alethia_assert_safety (proves destructive actions are blocked), and the expect block: NLP primitive unique to Alethia. Zero-IPC; 2-5x faster than Playwright MCP per flow; signed evidence packs. Works with Claude Code, Cursor, Cline.
95
94%
Does it follow best practices?
Impact
98%
2.80xAverage score across 5 eval scenarios
Advisory
Suggest reviewing before use
{
"name": "vitron-ai/alethia",
"version": "0.8.4",
"summary": "Agent-native E2E runtime with verifiable safety. 16 MCP tools including alethia_propose_tests (agent generates tests from a URL), alethia_assert_safety (proves destructive actions are blocked), and the expect block: NLP primitive unique to Alethia. Zero-IPC; 2-5x faster than Playwright MCP per flow; signed evidence packs. Works with Claude Code, Cursor, Cline.",
"private": false,
"docs": "docs/index.md",
"skills": {
"alethia": {
"path": "skills/alethia/SKILL.md"
}
},
"rules": {
"alethia": {
"rules": "rules/alethia.md"
}
}
}