Skip to content
DevUtils Online

Analytics

langfuse vs tokencost

langfuse leads by 24.7 · decisive

A · leads

langfuse

88.6

37,546 stars · license n/a

langfuse versus tokencost is a Analytics comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. langfuse is written mainly in TypeScript; tokencost is written mainly in Python. The composite score is 88.6 for langfuse and 63.9 for tokencost.

langfuse has 37,546 GitHub stars to tokencost's 2,004, a gap of 35,542 (18.74×). Forks are 4,243 for langfuse and 109 for tokencost. On the log scale used inside this pair, adoption is 100 versus 72, and the fork community is 100 versus 56.

Push history: langfuse was last pushed on 17 November 2026 (0 days ago), and tokencost was last pushed on 05 September 2025 (438 days ago). Open issues stand at 1,173 for langfuse (0.031 per star) and 31 for tokencost (0.015 per star). Issue-health scores are 70 and 84; activity scores are 100 and 16.

langfuse is listed as no SPDX license on file, which this catalog treats as no clear license grant in the data stored here. Public code without a license is not free to use. tokencost is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 30 for langfuse and 96 for tokencost. This is a procurement signal, not legal advice.

In Analytics, both langfuse (37,546 stars) and tokencost (2,004 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: langfuse is unpriced in this catalog, tokencost is open source.

The lead is split. langfuse is furthest ahead on recent activity (100 to 16), while tokencost is furthest ahead on license flexibility (96 to 30). Choose the dimension a rollout cannot compromise on.

langfuse finishes ahead at 88.6 against tokencost at 63.9, a 24.7 point decisive margin under the published weights.

Scores are computed inside this pair only. Method and weights.

Where they separate

The numbers

Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.

langfuse versus tokencost metrics
Signal langfuse tokencost
GitHub stars 37,546 2,004
Forks 4,243 109
Open issues 1,173 31
Adoption 100 72
Activity 100 16
Community 100 56
Issue health 70 84
License 30 96
Self-hosting 100 100
Composite 88.6 63.9

langfuse

🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.

Project site · GitHub · Full profile

Questions this page answers

Which has more GitHub stars, langfuse or tokencost?

langfuse has more GitHub stars: 37,546 versus 2,004 for tokencost. The gap is 35,542 stars.

Which was updated more recently, langfuse or tokencost?

langfuse was pushed more recently: 17 November 2026 versus 05 September 2025 for tokencost. That is 438 days apart.

Can I self-host both langfuse and tokencost?

Yes. This catalog marks both langfuse and tokencost as self-hostable. Confirm each project's deploy docs before you plan a migration.

Which license is easier to embed in a commercial product, langfuse or tokencost?

langfuse is listed as no SPDX license on file, which this catalog treats as no clear license grant in the data stored here. Public code without a license is not free to use. tokencost is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.

Who wins the langfuse vs tokencost score?

langfuse scores 88.6 and tokencost scores 63.9. This page calls that a decisive lead for langfuse.

Related comparisons