LLMxRay

LLMxRay is a Community listing on Launch Llama with 0 total upvotes, founded by Ivan Stankovic who joined in Oct 2026, compared against 6 alternatives.

Launched on Launch Llama Oct 26, 2026 · #52 of 111 that day

About

Key Features

• Streams model tokens in real time as they are generated
• Delivers compares multiple local models side by side in one view
• Delivers benchmarks models using real logprobs data
• Delivers inspects reasoning chains to see how decisions are made
• Runs fully locally against Ollama with no cloud costs
• Tracks chat, RAG, and metrics through a Vue-based interface

Use Cases

• Watching what VS Code Copilot, Open WebUI or Continue actually send to a local Ollama model, turn by turn, to find oversized prompts or broken cache reuse
• Comparing the same prompt across several local models side by side and checking token probabilities and benchmark logprobs
• Sending Ollama call traces as OpenTelemetry spans to Jaeger, Phoenix, Langfuse or Grafana to debug agent runs

Who it is for

• Developers running local LLMs on Ollama who want visibility into their tools' requests
• Engineers building or debugging AI agents that call a local Ollama model
• Teams evaluating and benchmarking local models before choosing one

Pricing

Alternatives

AI Observability by OpenObserveFor AI teams: OpenObserve monitors LLM agents with 140x lower storage costs than competitors so you debug production issues without breaking budgets.OllamaFor Apple users: Ollama runs large language models locally on Apple Silicon with MLX for faster coding and agent workflows.SpanlensFor developers: Spanlens logs every LLM API call with cost, latency, and tokens so you optimize spend and catch performance issues instantly.Future AGIFor AI engineers: traceAI captures prompts, completions, and agent decisions across 35+ frameworks, routing to your existing observability stack in two lines of code.What's my local ai?For AI engineers: What's my local ai? detects your hardware and recommends local models so you run LLMs privately without cloud costs.Markstream VueFor AI developers: Markstream Vue renders streaming Markdown across Vue, React, Next.js, and Svelte so users see AI responses in real-time.

Tags