Self-hosted alternatives to Spanlens
200 self-hosted apps like Spanlens, closest match first.
Top picks
- G
GoModel
LaunchAI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming,
Free
- L

Langfuse
LaunchTrace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
- R
Routerly.ai
LaunchSelf-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No da
Free
- O
OpenAgentCore
LaunchOpenAgentCore is an open-source, self-hosted version of the OpenAI Agents API. You talk to it through the official OpenAI SDK: you create a session, send it an input, and the Core runs the agent work and returns the result, keeping events a
Free
- O

OmniKey-AI-Unified-Key-Manager
LaunchA self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM platforms with automatic fallback, key scheduling, rate-limit tracking and encrypted credential storage
Free
- O
Open Responses
LaunchOpen Responses is a self-hosted, open-source alternative to OpenAI's Responses API. It is a drop-in replacement, so you can keep the code you wrote for the OpenAI Agents SDK and point it at your own server. It works with any large language
Free
More like Spanlens
About Spanlens
Spanlens
Drop-in observability platform for OpenAI, Anthropic, and Gemini
Spanlens is an observability platform for LLM applications that works with OpenAI, Anthropic and Gemini, and with other providers such as Groq, Mistral, xAI and OpenRouter. To start, you change one line of config, the provider base URL, and your SDK call stays the same. Every model call is logged with its cost, latency and tokens, and you can see spend per model and project, including cache savings. It flags cost spikes, error bursts and latency drift, and shows the model and project responsible. You can pin prompt versions and compare cost and quality on real traffic. Exact-match caching can be switched on with a header, so repeat calls skip the provider. Evals can run in CI to gate a merge, and agent traces show nested spans across tools, retrievals and model calls. PII detectors flag things such as card numbers and email addresses without blocking the request. Spanlens is open source under the MIT licence and can be self-hosted with Docker, or used as a hosted service with a free plan and a Pro plan.
- Price
- Freemium
- Category
- AI
- Website
- spanlens.io

