Langfuse provides open-source evaluation and observability tools for tracing and improving AI agents.
OpenLIT
OpenLIT provides observability and evaluation for AI agents and coding agents, tracing models, tools, prompts, costs, and workflows.

About OpenLIT
OpenLIT is an open-source platform for tracing, evaluating, and guarding AI agents and coding agents. It uses OpenTelemetry to record LLM calls, tool calls, retrieval, and agent steps, and adds evaluations, guardrails, prompt and context management, and cost and GPU monitoring. It is free to self-host under the Apache 2.0 license. The homepage lists support for Claude Code, Codex, Cursor, OpenAI Agents SDK, LangGraph, CrewAI, and more than 70 other integrations.
Setup starts with Docker Compose to run the service locally, followed by the Python or TypeScript SDK to instrument an application. Automatic instrumentation applies to supported LLM providers, frameworks, and vector databases, so coverage depends on what is supported. Pricing for any hosted use is not stated on the homepage.
Key features
- OpenTelemetry-native tracing of LLM calls, tool calls, retrieval, and agent steps
- Observability view of coding-agent sessions from Claude Code, Cursor, Codex, and Windsurf
- Evaluations using LLM-as-a-judge, programmatic checks, and human feedback, with CI gates
- Runtime guardrails for prompt injection, sensitive topics, and topic restriction
- Prompt Hub, context management, Rule Engine, and Vault for secrets
- Cost tracking with custom pricing and GPU monitoring for NVIDIA, AMD, and Intel
- Free to self-host under the Apache 2.0 open-source license.
- Exports traces and metrics using OpenTelemetry.
- Automatically instruments supported LLM providers, frameworks, and vector databases after openlit.init().
- The quickstart runs the platform through Docker Compose, so users need Docker to run it locally.
- Automatic instrumentation only covers supported providers and frameworks.
OpenLIT at a glance
- Website
- github.com/openlit/openlit
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
OpenLIT alternatives
Tools and sites you could use instead, ranked by how closely they match.
Observability and prompt management platform for LLM-based apps. Take your LLMs to the next level.
agenttrace audits coding-agent sessions, tracking costs, tokens, latency, failures, and health.
Kitaru provides agent traces that teams can run and inspect during application workflows.
This SDK provides AI evaluations, prompt management, and observability for Python and TypeScript workflows.
Future AGI evaluates and observes AI and agent applications with tracing, simulations, datasets, and guardrails.
Popular in AI Infrastructure & MLOps
Well-known listings from the same topic.
OpenLIT FAQ
Is OpenLIT free to use?
How does an application send telemetry to OpenLIT?
Which coding agents does the CLI support?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












