Open-source AI infrastructure
Six self-hosted LLM observability tools compared on the things that actually decide adoption: the real licence, which features a licence key gates, how many datasto…
If you want the fastest start, Phoenix runs on SQLite from a pip install, though its licence is source-available rather than open source. If you want the largest community and the most complete self-hosted build, Opik is the obvious first look. If you want the smallest thing to operate, OpenLIT runs on one datastore and has no paid tier at all. If you are already committed to OpenTelemetry and want to keep your data…
Licence: MIT core, plus a separate Langfuse Enterprise Licence over ee/, web/src/ee/ and worker/src/ee/. This is the single most misread fact in the category. The headline "MIT" is true and the core really is free to self-host without usage limits. But nine features are gated behind a licence key when self-hosting: project-level RBAC, protected prompt labels, data retention policies, audit logs, server-side data mas…
Licence: Apache-2.0, copyright Comet ML. No ee/ directory in the repository. Commercial differentiation happens entirely at the hosted-Comet layer rather than through a licence carve-out, which is a meaningfully more honest structure than the alternative.
Licence: Apache-2.0. No ee/ directory. No paid tier exists today at all.
Licence: Apache-2.0. No enterprise directory. 7,409 stars as of August 2026.
Licence: Apache-2.0, in LICENSE.md rather than LICENSE, which is why some licence scanners misreport it. No ee/ directory. 3,212 stars as of August 2026, pushed the same day it was checked.