Nikhil Pareek

Hey Dev Hunt community! Nikhil here, Founder & CEO at Future AGI. Today, I’m really excited to share Agent Compass, something no other Agent monitoring or evaluation tool offers and we are the first one. Why did we build this? Over the past few months, I kept seeing the same problem across AI teams: debugging agents is chaotic. Teams would spend hours digging through logs and dashboards, trying to piece together why an agent failed. One small change in a prompt, a tool, or a data source could cascade into errors that nobody could fully trace. I’ve literally watched engineers spend days chasing failures, only to realize the root cause was something completely unexpected. And to make things worse, the current evaluation tools don’t really help. They just flag that something broke, without giving any clue about why or how to fix it. How does it actually work? Agent Compass is a zero-config evaluation tool for AI agents. It automatically identifies issues like hallucinations, traces their causes across prompts, tools, retrievals, and guardrails, and suggests fixes that teams can apply right away. Instead of looking at errors one by one, it shows patterns across your entire agent fleet, making debugging faster and more reliable. It builds a truth graph for your agents by linking errors across prompts, tools, and execution steps. It automatically clusters failures into a small set of root causes and generates an error tree that shows how one issue cascades across the workflow. Instead of drowning in fragmented traces and logs, you get a clear narrative of what broke, why it happened, and how to fix it. With zero-config evals, setup takes just a few lines of code. Debugging stops being a full-time job and starts becoming a fast, reliable process. Where we’re headed This is revolutionary. The vision is to make AI agents as reliable and predictable as traditional software, no matter how complex their workflows become. This will bring us closer to true autonomous reliability. Thanks for checking this out. I’d love to hear your thoughts, and how your team handles debugging multi-tool AI agents today! ▶️ Debug your AI agents in 5mins. - Try Agent Compass for free-> https://shorturl.at/yVWSb - Tech Docs -> https://shorturl.at/0ATkG - Research Paper -> https://shorturl.at/91n0w

Hey DevHunt! 👋 I'm Nikhil from Future AGI, and I'm excited to share traceAI with you today. The Problem We're Solving If you're building with LLMs, you know the pain: your agent made 34 API calls, burned through your token budget, and returned the wrong answer. You have no idea why. Existing LLM tracing tools force you into a new vendor dashboard. But most teams already have observability infrastructure - Datadog, Grafana, Jaeger. Why add another? OpenTelemetry is the industry standard for application observability, but it was designed before AI existed. It understands HTTP latency. It has no concept of prompts, tokens, or reasoning chains. What traceAI Does??? traceAI is the proper GenAI semantic layer on top of OpenTelemetry. It captures everything that matters in your AI application: - Full prompts and completions - Token usage per call - Model parameters and settings - RAG retrieval steps and sources - Agent decisions and tool executions - Errors with full context - Latency at every layer And sends it to whatever observability backend you already use. Two lines of code: from traceai import trace_ai trace_ai.init() Your entire GenAI app is now traced automatically. Works with everything: - Languages: Python, TypeScript, Java, C# (with full parity) - Frameworks: OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, DSPy, Bedrock, Vertex AI, MCP, Vercel AI SDK, and 35+ more - Backends: Datadog, Grafana, Jaeger, or any OpenTelemetry-compatible tool - Actually follows GenAI semantic conventions. Not approximately. Correctly. So your traces are readable in any OTel backend without custom dashboards or parsing. - Zero lock-in. Your data goes where you want it. Switch backends anytime. We don't even collect your traces. - Open source. Forever. MIT licensed. Community-owned. We're not building a walled garden. Who Should Use This??? AI engineers debugging complex LLM pipelines Platform teams who refuse to adopt another vendor Anyone already running OTel who wants AI traces alongside application telemetry Teams building agentic systems who need production-grade observability What's Next??? We're actively working on: - Go language support - Expanded framework coverage Try It Now ⭐ GitHub: https://shorturl.at/GT9KZ 📖 Docs: https://shorturl.at/Yz8zv 💬 Discord: https://shorturl.at/zHp8Y