AI Potluck
Contribute
Back to Gap Map Product / UX / Telemetry & observability

OpenLIT

OpenLIT
open source / Overall score: 3.5

OpenTelemetry-native AI engineering platform covering LLM observability, GPU monitoring, guardrails, evaluations, and prompt management. Integrates with 50+ LLM providers, vector databases, and agent frameworks. Vault for managing API keys, plus a rule engine and a playground. Differentiated by breadth of integrations and GPU-level monitoring, and self-hostable from the repository's docker-compose file.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public
core features withheld
no

Fully Apache-2.0, OpenTelemetry-native, no feature-gated core; vendor-neutral by design (exports to any OTel backend).

  • https://docs.openlit.io/latest/openlit/installation recorded 2026-09-29

    Self-host docs: "OpenLIT is open source and is lightweight to self-host." with Docker Compose and Helm deployment steps and no license key or enterprise build mentioned.

  • https://github.com/openlit/openlit recorded 2026-08-13

    Repository page. License resolves to Apache-2.0 (spdxId "Apache-2.0"); the README strapline reads "OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground" and the root listing includes docker-compose.yml with no ee/ or enterprise directory beside it. 2,686 stars.

  • https://openlit.io/ recorded 2026-09-29

    Home page: "Core platform Apache 2.0 licensed" and "Inspect the code, self-host for free with no license key"; also labels an eBPF controller as Enterprise.

  • https://openlit.io/pricing recorded 2026-09-29

    Pricing page: "OpenLIT OSS is free to self-host under Apache 2.0 with no license key and no per-trace fee." and "Apache 2.0 licensed OpenLIT platform".

  • https://pypi.org/pypi/openlit/json recorded 2026-09-29

    PyPI metadata for openlit: "License :: OSI Approved :: Apache Software License" and license "Apache-2.0".

Adoption

3 high confidence
3.0

Adoption is measured by monthly PyPI downloads of the openlit SDK, treated as the platform's own reach since installing it installs OpenLIT rather than a separate client. GitHub stars describe a smaller community than Langfuse or MLflow, consistent with a reading below both.

Capability

4 high confidence
4.0

OpenLIT covers OpenTelemetry-native tracing and metrics for LLMs, agents, vector databases and GPUs, LLM-as-a-judge and programmatic evaluations, a versioned Prompt Hub, cost tracking, guardrails and a secrets vault, with integrations across more than ninety providers and frameworks. That breadth keeps it level with Langfuse.

  • https://docs.openlit.io/ recorded 2026-09-29

    Docs overview: "OpenLIT is an open-source AI Engineering platform for LLM observability, evaluations, prompt management, and cost tracking - built on OpenTelemetry, fully self-hostable." plus Prompt Hub, OpenGround, Rule Engine, Vault and Evaluations in navigation.

  • https://docs.openlit.io/latest/openlit/evaluations/overview recorded 2026-09-29

    Evaluations page: "Score production traces with an LLM-as-a-judge, enable built-in or custom evaluators, schedule Auto Evaluation, and review pass-rate analytics".

  • https://github.com/openlit/openlit recorded 2026-08-13

    README strapline - "OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground" - and a section headed "Observability, Evaluations, Rule Engine, Guardrails, Prompts, Vault, Playground", with integrations across 50+ LLM providers and vector databases.

  • https://openlit.io/pricing recorded 2026-09-29

    Pricing OSS feature list: "Prompt versioning", "Encrypted storage (AES-256-GCM)", "Built-in guards in SDK (LLM and regex)" and "GPU utilization, memory, temperature, and power visibility." all listed as included in free OSS.

Verified 2026-09-24