Spanlight

    Spanlight

    No reviews
    Category:Coding & Development
    Pricing:Free
    Added:
    Updated:
    Website:
    VISIT NOW

    Share

    Spanlight is an open-source LLM observability platform: traces, line-by-line spend, a gateway, failure detectors, prompts and evals on a single Postgres.

    What is Spanlight?

    Spanlight is an open-source AI tool for LLM observability. It traces every call, computes its spend line by line, checks it against what your provider reports and helps you find out why it failed, all self-hosted on a single Postgres database.

    What is Spanlight used for?

    It shows what your AI apps and agents do and how much they spend. Each call lands within seconds with prompt, completion, latency, tokens and spend, and you can read a session turn by turn. When an amount cannot be known, Spanlight shows a dash with the reason, never a zero. Every day it compares traced data with Anthropic or OpenAI figures, and lets you attribute spend by customer, feature or team with metadata, plus budget scopes that alert or block.

    How does Spanlight work?

    Send traces with the Python SDK (wrapping your OpenAI or Anthropic client), any OTLP exporter (it reads GenAI conventions, OpenInference, OpenLLMetry and the Vercel AI SDK) or through its gateway, changing only the base URL. The gateway adds sealed credentials, retries and fallbacks, and per-key rate limits. Every 15 minutes the Doctor runs 16 detectors over your spans, such as repeated tool calls, misconfigured client timeouts or latency regressions, each with evidence and a suggested fix.

    Who is Spanlight for?

    • Teams shipping LLM apps and agents to production.
    • Developers debugging failures in model calls.
    • Managers who need to attribute AI spend.
    • Companies that prefer to self-host observability.

    Spanlight pros and cons

    It includes prompt management with versions, labels, a playground and exact replay of recorded calls, evals with 95% confidence intervals and a nightly queue of traces worth reading. Its core is MIT licensed and deploys with Docker Compose. On the downside, the server is still a pre-1.0 release.

    Spanlight features and use cases

    •Live traces with prompt, completion, latency, tokens and spend.
    •Line-by-line spend, with a reason when it cannot be known.
    •Daily reconciliation with Anthropic or OpenAI data or a CSV.
    •Attribution by customer, feature or team via metadata.
    •Budget scopes that alert on or block spend.
    •Doctor with 16 failure detectors every 15 minutes and suggested fixes.
    •Gateway compatible with official OpenAI and Anthropic SDKs, with retries and per-key limits.
    •Python SDK and OTLP ingestion (OpenInference, OpenLLMetry, Vercel AI SDK).
    •Versioned prompts, playground, exact replay and evals with 95% CIs.
    •Self-hosted on a single Postgres with an MIT core.
    •Use case: a support bot repeats reserve_item with the same arguments and the Doctor flags it with evidence and a fix.
    •Use case: a team blocks a prompt change in CI that lowers its eval pass rate.

    How to use Spanlight

    1Clone the repository and set up the env file.
    2Start the platform with Docker Compose.
    3Install the SDK with pip install spanlight.
    4Wrap your OpenAI or Anthropic client, use OTLP or point the base URL at the gateway.
    5Check that the first trace shows up in the dashboard.
    6Connect provider data for reconciliation.
    7Review Doctor findings and create evals.

    Spanlight FAQ

    What is Spanlight?

    Spanlight is an open-source LLM observability platform that traces calls, computes their spend and detects failures.

    Is Spanlight free?

    It is open source and self-hostable with no paid license; details are in the pricing section.

    How do I send traces?

    With the Python SDK, any OTLP/HTTP exporter or through the gateway by changing the base URL.

    What is the Doctor?

    A set of 16 detectors that check your spans every 15 minutes and return evidence, a suggested fix and a way to verify it.

    How does it reconcile spend with my provider?

    It compares traced data daily with figures pulled using an Anthropic or OpenAI admin key, or a CSV upload.

    What do I need to host it?

    Docker Compose and Postgres, its only datastore, job queue included.

    Can it evaluate prompts?

    Yes, with versions, a playground, exact replay and evals with pass rates and 95% confidence intervals.

    Does Spanlight have an API?

    Yes, an API reference, an OTLP endpoint at /v1/otlp/traces and a gateway compatible with OpenAI and Anthropic APIs.

    Does Spanlight work in Spanish?

    The interface and docs are in English; traces record content as sent, in any language.

    What are the alternatives to Spanlight?

    In our directory you can compare it with Langfuse and Arize AX for LLM observability, or Evalship for evals.

    Spanlight pricing and plans

    Reference amounts in US dollars (USD). Checked on: 17/11/2026.

    Spanlight is open source (MIT-licensed core) and self-hosted on Postgres with no license fee. The site does not publish prices for a hosted version; server costs are on you.

    Spanlight Screenshots

    Spanlight screenshot 1
    Spanlight screenshot 2

    Spanlight user reviews

    Write a review

    Checking your session...

    Spanlight Reviews

    Loading reviews...

    Spanlight alternatives

    Woolly
    Free

    Woolly

    Woolly is an open-source memory engine for AI agents: one local Markdown folder your tools share over MCP, an API and SDKs.

    –
    15
    Coding & DevelopmentEducation & TranslationOffice & Productivity
    Shotoku
    Freemium

    Shotoku

    Shotoku is an open-source authorization engine that enforces budgets and approvals on AI agent spending before payment, locally and without holding funds.

    –
    18
    Coding & DevelopmentOffice & Productivity
    Liquid Inference
    Paid

    Liquid Inference

    Liquid Inference is an LLM inference exchange where providers compete in an instant auction to answer each request at the best price and quality.

    –
    18
    Coding & DevelopmentOther
    Hubzoid
    Free

    Hubzoid

    Hubzoid is an open-source, self-hostable platform for internal AI agents: one shared brain for chat, workflows and MCP, with per-person permissions.

    –
    15
    Business ManagementCoding & DevelopmentOffice & Productivity
    datatomcp
    Freemium

    datatomcp

    datatomcp is a data layer for AI agents: connect databases, sheets and apps once, and Claude, ChatGPT or Cursor query exact answers over MCP or REST.

    –
    12
    Coding & DevelopmentResearch & Data Analysis
    Griyd
    Paid

    Griyd

    Griyd is a platform for teams coding with AI agents: ideas become reviewed specs on a shared board, and each developer's agent builds on its own story branch.

    –
    15
    Coding & Development

    Spanlight Analytics

    Views
    Real data
    Website Clicks
    Real data
    CTR
    Real data

    Views Trend (30 days)

    Analytics data is updated in real-time and is 100% real