OpenLIT
Open-source LLM and AI-agent observability built on OpenTelemetry.
At a glance
- Editor score9.0 / 10
- PricingFree plan
- Best forSelf-hosting teams needing broad infrastructure visibility
- Free planYes
- Paid fromNone
- LLM tracingYes
- Facts checked20 Sep 2026
Where it wins
- OpenTelemetry tracing covers LLMs, tools, agents, prompts, and retrieval
- Tracks tokens, costs, latency, errors, performance, and GPU metrics
- Apache 2.0 license with unlimited self-hosted usage in the OSS plan
Where it doesn't
- Deployment is centered on self-hosting with Docker or Kubernetes
- Community support is provided through GitHub for the OSS plan
- The Cloud plan lists pricing shared at launch
Our verdict on OpenLIT
OpenLIT is an open-source AI engineering and observability platform for teams building LLM applications, AI agents, and retrieval-augmented systems. Its OpenTelemetry-based tracing covers LLM calls, tools, agents, prompts, and retrieval, while the platform adds evaluations, prompt management, model comparison, dashboards, secret storage, and GPU monitoring. It fits engineering teams that want broad visibility across application behavior, infrastructure, and model operations while retaining control of deployment.
The published OSS plan costs 0 for self-hosted usage, is Apache 2.0 licensed, and includes unlimited self-hosted usage. It covers LLM tracing, evaluations, prompts, and agent monitoring, with community support on GitHub. OpenLIT can be deployed with Docker or Kubernetes across web, Windows, macOS, Linux, API, and self-hosted environments. A Cloud plan is described as a fully hosted platform with managed infrastructure and upgrades, with pricing shared at launch. Teams choosing OpenLIT should therefore be prepared to operate the OSS deployment or evaluate the hosted offering when available.
Its feature breadth is a central strength. OpenLIT supports automated evaluations with built-in and custom evaluators, Prompt Hub versioning and rollback, token and cost tracking, RAG and vector-database observability, custom ClickHouse-backed dashboards, and GPU utilization, memory, temperature, and power monitoring. Integrations span OpenAI, Anthropic, Azure OpenAI, Amazon Bedrock, Vertex AI, Mistral, Cohere, Ollama, vLLM, Hugging Face, Groq, NVIDIA NIM, and others. Choose it for a wide, self-hosted view of LLM and AI-agent systems; teams seeking a managed-first deployment should consider the Cloud plan's availability and pricing before selecting it.
OpenLIT pricing
All 2 OpenLIT plans and prices →
OpenLIT fact sheet
| Free plan | Yes |
|---|---|
| Paid from | None |
| LLM tracing | Yes |
| LLM evaluations | Yes |
| Prompt management | Yes |
| Agent tracing | Yes |
| Retrieval tracing | Yes |
| Token cost tracking | Yes |
| Deployment options | Self_hosted |
| Deployment | Self-hosted |
| Platforms | Web, Windows, macOS, Linux |
| Support | Community, Docs, Email |
| Built for | Small business, Mid-market, Enterprise (editorial estimate) |
| Integrations | 70+ integrations: OpenAI, GPT4All, Ollama, DeepSeek, Cohere, Anthropic … See all → |
| Pricing | Free plan (source) |
| Website | openlit.io |
| Facts checked | 20 Sep 2026 |
OpenLIT integrations
OpenLIT lists 70+ integrations on its own site — the 20 named here are the ones its pages call out.
- OpenAI
- GPT4All
- Ollama
- DeepSeek
- Cohere
- Anthropic
- vLLM
- Azure OpenAI
- Mistral
- Hugging Face
- Amazon Bedrock
- Vertex AI
- Google AI Studio
- Groq
- NVIDIA NIM
- xAI
- ElevenLabs
- Replicate
- Together.ai
- ChromaDB
See all OpenLIT integrations →
Alternatives to OpenLIT
- Arize AXBroad LLM observability with tracing, evaluations, prompts, agents, RAG, and cost tracking.9.0
- LangfuseA broad observability platform with open-source deployment and accessible paid tiers.9.0
- Arize PhoenixA free platform for tracing, evaluating, and improving LLM applications.9.0
See all OpenLIT alternatives →
Also listed in
Used OpenLIT? Be the first to review it
The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used OpenLIT for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.
Write a reviewTwo minutes · verified accounts only · read by an editor before it appears
Featured on iTechGuides
OpenLIT is listed in our LLM Observability Tools directory. Add the badge to your site — it links back to this page.
<a href="https://www.itechguides.com/products/openlit/"><img src="https://www.itechguides.com/best/badge/openlit.svg" alt="Featured on iTechGuides" width="230" height="46"></a>
Reviewed by iTechGuides Editors · Editorial team · Updated Sep 2026
Advertiser disclosure: iTechGuides is reader-supported. We may earn a commission when you click some links. It never changes a score or a verdict. How we rank.