Spanlens
MIT-licensed LLM observability with one-line setup, agent tracing, PII detection and cost anomaly alerts
0Visit Spanlens
www.spanlens.ioAbout Spanlens
Spanlens is an MIT-licensed LLM observability platform whose main design goal is that instrumenting an application should cost one line rather than an afternoon. A CLI initialiser rewrites the call sites for you, after which every OpenAI, Anthropic and Gemini request is logged with its cost, latency and token counts, and multi-step agent workflows are traced into a Gantt view that shows where the time and money actually went. Beyond straight logging it runs three checks that most cost dashboards do not: anomaly detection on a three-sigma basis, PII and prompt-injection detection on request content, and a model recommendation pass that proposes cheaper models with a dollar-figure saving attached rather than a vague suggestion. Recent SDK releases added Ollama support for local models and LangGraph tracing, so self-hosted and graph-structured agent stacks are covered alongside the hosted APIs. The licensing position is the sharpest part of the pitch: the vendor states the project is fully MIT with no `ee/` folder, meaning there is no enterprise-only directory carved out of the open-source repository — self-host with Docker Compose and every feature listed on the paid tiers is available at zero cost. The hosted tiers exist to sell managed retention, seats and alerting rather than to gate functionality, and the site publishes direct comparisons against Langfuse and Helicone.
Does ChatGPT recommend your AI tool?
If you're building in AI Agent Infrastructure, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.
Key Features
Spanlens Pros & Cons
✅ Pros
- +No open-core carve-out — self-hosting gets every paid feature
- +PII and prompt-injection checks come standard rather than as a security add-on
- +Cost recommendations are quantified in dollars, not left as advice
⚠️ Cons
- −Hosted free tier hard-429s at 50K requests instead of degrading gracefully
- −Provider coverage is OpenAI, Anthropic, Gemini and Ollama — narrower than gateway-style tools
- −Retention on Pro tops out at 90 days
Tags
Is Spanlens your tool?
This is the page buyers and AI assistants read when they look up Spanlens. Claim your listing for $19 one-time — no subscription, nothing to cancel — and take a capped slot in your category: each one sells a fixed number, and yours ranks above every free tool in it, with a Featured badge. Prefer it ongoing? Monthly is one click away on the next page.
Complete Your AI Agent Stack
Other ai agent tools in our catalog:
1Password
Try FreeSecrets and credential manager
Keep API keys and .env secrets out of your repo
Consensus
Try FreeAI search across 200M research papers
Source real evidence behind your analysis
Gamma
Try FreeAI presentation builder
Turn ideas into polished decks instantly
💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.
Stay updated on AI Agent Infrastructure tools — join our weekly newsletter
One concise email with fresh launches, trending picks, and featured standouts.
Alternatives to Spanlens
View all Spanlens alternatives →More AI Agent Infrastructure tools
Cognilode
AI agents that resolve real production failures against observable acceptance criteria.
GuGuData.AI
GuGuData.AI — description pending review.
Pragor
Shared operations board for AI agents and human teams
Spectrum by Photon
Open-source framework connecting AI agents to iMessage, WhatsApp, Telegram, Slack, Discord and Instagram
Spix
Voice, SMS and email infrastructure for AI agents — MCP-native, ~500ms call latency, CLI-first
Statey
A hosted, MCP-native database that keeps structured, attributed state across every AI chat client
Agent connectivity: not yet verified