Launching today
AgentTrace
Open-source circuit breaker for AI agent pipelines
4 followers
Open-source circuit breaker for AI agent pipelines
4 followers
Agent 1 hallucinates. Agent 2 builds on it. Agent 3 executes. All returned 200 OK. Nobody knew. AgentTrace is the open-source circuit breaker for AI agent pipelines: - 14 rules: hallucination, PII, prompt injection, rate limiting, OWASP LLM, EU AI Act - One agent blocked = downstream agents never run - Live dashboard, zero cloud, 100% local audit trail - Python + TypeScript full parity 2 lines to add. Works with LangChain, CrewAI, OpenAI. MIT licensed. 200+ tests.
Hey Product Hunt 👋
I'm Kalash, maker of AgentTrace.
𝗧𝗵𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺: Three months ago I was debugging a multi-agent AI pipeline. Agent 1 (researcher) returned bad data, a hallucinated number. Agent 2 (drafter) built a report on it. Agent 3 (executor) sent it to customers. Every single one returned 200 OK. Nobody in my logs caught it.
We have observability for infrastructure, but zero accountability for AI agents. That's the gap AgentTrace fills.
𝗪𝗵𝗮𝘁 𝗶𝘁 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝗱𝗼𝗲𝘀:
→ Wraps any agent in 2 lines of code
→ 14 compliance rules run in parallel (PII, hallucination, prompt injection, EU AI Act...)
→ One agent violates a rule → entire pipeline stops, downstream agents never execute
→ Full audit trail with UUIDs you can look up months later
→ Live dashboard with risk distribution, pipeline monitor, violation details
It's not just logging. It's pre-mortem intervention.
𝗧𝗵𝗲 𝗵𝗮𝗹𝗹𝘂𝗰𝗶𝗻𝗮𝘁𝗶𝗼𝗻 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 is worth mentioning. It works without calling another LLM. Extracts numeric values, normalizes units, checks against your RAG context. Agent says "8000mg" but your source says "2000mg" → blocked with 0.98 confidence.
𝗪𝗵𝘆 𝗠𝗜𝗧: I want every AI team to have this, not just the ones with $50k/year security budgets. The SDK, rules engine, and dashboard are free forever.
GitHub: github.com/kalash33/agenttrace
Kalash