Scale3 Labs

license

AGPL-3.0(OSI, copyleft, the application)

source

public

core features withheld

no — the whole AGPL-3.0 application is in the repository - app, components, lib, prisma, proto, Dockerfile, docker-compose.yaml - with no ee/ or enterprise directory, no second license and no license-key check, and the vendor's FAQ says Langtrace Cloud is not charged for

Langtrace's whole AGPL-3.0 application ships in the repository, with no enterprise directory, second license or license-key check, and self-hosting is a documented first-class path. The SDKs are separately Apache-2.0, and the vendor's FAQ says the hosted Cloud tier is not currently charged for, so neither license withholds anything from the published source.

• https://api.github.com/repos/Scale3-Labs/langtrace/contents/ recorded 2026-08-12

  Repository root, listed to test for a carve-out. Dockerfile, LICENSE, README.md, SECURITY.md, app, components, lib, prisma, proto, public, scripts, middleware.ts, docker-compose.yaml and the Next.js config files. There is no ee/, no enterprise/, no second LICENSE below the root, and no license-key module. GitHub's license endpoint returns AGPL-3.0 for the single root LICENSE. The published tree is the whole application and it self-hosts from the docker-compose file in it.

• https://github.com/Scale3-Labs/langtrace recorded 2026-06-04

  AGPL-3.0 app license, Apache-2.0 SDKs, OTel-based observability

• https://github.com/Scale3-Labs/langtrace/releases recorded 2026-06-04

  app v4.0.11 release 17 Apr 2026 (active)

• https://raw.githubusercontent.com/Scale3-Labs/langtrace/main/README.md recorded 2026-08-12

  The vendor's own statement of the split and of the cloud tier. License section: "Langtrace application(this repository) is licensed under the AGPL 3.0 License" and "Langtrace SDKs are licensed under the Apache 2.0 License." The feature list includes "Self-hosting Option: Deploy on your own infrastructure", and the FAQ answers "Can I self host and run Langtrace in my own cloud?" affirmatively. On price: "What is the pricing for Langtrace cloud? Currently, we are not charging anything for Langtrace cloud and we are primarily looking for feedback so we can continue to improve the project. We will inform our users when we decide to monetize it." A cloud tier that charges nothing cannot be the paid tier a core is withheld for.

Langtrace is a self-hostable server with a hosted cloud beside it. Its Python SDK is left out because applications install it to send traces, so its downloads count instrumented applications rather than Langtrace deployments. The score comes from Docker Hub pulls of the server image that the repository's docker-compose file runs, averaged over the image's lifetime, so for a growing product it is a floor. The hosted cloud publishes no usage figure and is not counted.

• https://hub.docker.com/v2/repositories/scale3labs/langtrace-client/ recorded 2026-09-24

  "pull_count": 21148 cumulative pulls of scale3labs/langtrace-client, "date_registered": "2024-03-28", "last_updated": "2025-04-17", about 700 a month over the image's lifetime

• https://pypistats.org/api/packages/langtrace-python-sdk/recent recorded 2026-09-24

  "last_month":15156 downloads of langtrace-python-sdk, the client package left out of the level

• https://raw.githubusercontent.com/Scale3-Labs/langtrace/main/docker-compose.yaml recorded 2026-09-24

  The self-hosting compose file. Its langtrace-app service runs "image: scale3labs/langtrace-client:latest" beside postgres and clickhouse, so the Docker Hub image is the server a self-hosted install pulls.

• https://ungh.cc/repos/Scale3-Labs/langtrace recorded 2026-09-24

  "stars":1232 for Scale3-Labs/langtrace. Corroboration only; a star count is not a use.

Langtrace provides real-time OpenTelemetry-native tracing across LLMs, frameworks and vector databases, with evaluations, prompt management through a registry API, annotations, a model playground, and cost and usage analytics. Its evaluations run on manually annotated datasets and compare results across models, with no automated judge-based scoring in the documentation, which keeps it a step behind Langfuse.

• https://docs.langtrace.ai/introduction recorded 2026-09-29

  Docs introduction: "is an open-source observability tool that collects and analyze traces in order to help you improve your LLM apps", traces are "based on the OpenTelemetry standard", and the navigation lists "Manage Prompts", "Prompt Registry APIs", "Evaluations", "Compare Evaluations", "Annotations" and "Model Playground".

• https://github.com/Scale3-Labs/langtrace recorded 2026-08-13

  Repository description - "observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more" - with repository topics including datasets, evaluations, llmops and observability. The README Features list itself names Open Telemetry Support, Real-time Monitoring, Performance Insights and Debug Tools.