Spanlens

About Spanlens

Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Azure OpenAI, or a local Ollama model. Integration takes one line: swap your client's baseURL to the Spanlens proxy, or run "npx @spanlens/cli init" and the wizard rewrites your code automatically. From that moment, every request is recorded with its model, token counts, latency, cost, and full prompt and response body, with streaming responses reconstructed automatically. The dashboard turns that raw log into operational insight. Cost tracking breaks spend down per request, per model, and per end user, and parses prompt-cache tokens separately so you see real cache savings rather than sticker price. Agent tracing visualizes multi-step workflows as Gantt waterfalls and node-and-edge graphs, highlighting the critical path so you can find the slowest dependency chain in a fan-out. Anomaly detection flags 3-sigma deviations in latency, cost, or error rate against a rolling 7-day baseline with root-cause hints. Alerts on budget, error rate, and p95 latency are delivered to Email, Slack, or Discord. Spanlens goes beyond passive logging. A regex-based PII and prompt-injection scanner inspects request and response bodies and can block injections at the proxy. The savings engine spots calls that match a cheaper model's profile (for example, a gpt-4o call that looks like a classification task) and estimates the monthly saving from switching. Prompt versioning with A/B experiments compares versions on latency, cost, and error rate using Welch's t-test for statistical significance, and an LLM-as-judge evaluation framework (judge with OpenAI, Anthropic, or Gemini) scores outputs against rubric anchors, with human agreement measured by Pearson r or Cohen's kappa. Reusable datasets power offline evals and regression checks. As a tool in the productivity space, Spanlens is purpose-built for founders who need to run a leaner startup without unnecessary complexity. It's designed for speed — most founders can get started within minutes and see tangible results within their first week of use. Spanlens works well for solo founders running lean operations as well as small teams looking to scale efficiently. Whether you're bootstrapping or backed by investors, the core value proposition remains the same: helping you run a leaner startup with less friction and fewer resources than traditional alternatives.

How Founders Use Spanlens to Run a leaner startup

Here's how founders use Spanlens to run a leaner startup:

• Use Spanlens to run a leaner startup by integrating it into your daily workflow from day one.
• Pair Spanlens with your existing stack to run a leaner startup without overhauling your workflow.

Key Features for Founders

• Spanlens is an open-source (MIT) LLM observability platform that lets developers monitor every call their application makes to OpenAI, Anthropic, Gemini, Mistral, OpenRouter, Azure OpenAI, or a local Ollama model
• Integration takes one line: swap your client's baseURL to the Spanlens proxy, or run "npx @spanlens/cli init" and the wizard rewrites your code automatically
• From that moment, every request is recorded with its model, token counts, latency, cost, and full prompt and response body, with streaming responses reconstructed automatically
• Built for founders who want to run a leaner startup using productivity tools
• Minimal setup — start seeing results in minutes, not weeks
• Scales with your team from solo founder to growing startup

Spanlens Pricing

Pricing details for Spanlens are available on their official website. Many tools in this category offer free tiers or trials.

Frequently Asked Questions

Other Tools to Run a leaner startup

• AppPulse 4 upvotes
• AICostPass 8 upvotes
• PulseCare 8 upvotes
• Telemetry.host 2 upvotes