We just launched asqav on Hacker News - quantum-safe audit trails for AI agents

Just submitted asqav to Hacker News: https://news.ycombinator.com/item?id=47665415

asqav is an open-source Python SDK that signs every AI agent action with ML-DSA-65 (quantum-safe, FIPS 204). Three lines to add tamper-evident audit trails to any agent framework.

pip install asqav

import asqav
asqav.init(api_key=\"sk_...\")
agent = asqav.Agent.create(\"my-agent\")
agent.sign(\"api:call\", {\"model\": \"gpt-4\"})

Works with LangChain, CrewAI, OpenAI Agents, Haystack, LiteLLM. MCP server for Claude Desktop. MIT licensed.

We built this because the EU AI Act Article 12 requires tamper-evident logging by August 2026, and nothing existed that was both cryptographically serious and easy to integrate.

GitHub: https://github.com/jagmarques/asqav-sdk
Docs: https://asqav.com/docs/
MCP server: https://github.com/jagmarques/asqav-mcp
Compliance scanner: https://github.com/jagmarques/asqav-compliance

If you find it useful, a star on GitHub helps others find it.