WE

Weave

Toolkit for tracking and evaluating LLM applications

Self-Hosted AI ★ 1.1k stars Medium setup Apache-2.0

Weave is a lightweight toolkit from Weights & Biases for logging, tracing and evaluating LLM application calls. The tracing server component can be self-hosted to keep AI evaluation data on your own infrastructure.

Key features

  • LLM call tracing
  • Evaluation framework
  • Self-hostable server
  • Python-native

Strengths

  • Released under the Apache-2.0 license
  • First-class Docker support for quick deployment
  • Active community (1.1k GitHub stars)
  • Written in Python

Is Weave secure?

No known vulnerabilities affect Weave's latest release (v0.53.12). OSV.dev lists 1 past advisory for the project; none of them applies to this release. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

  • Most recent fixed advisory CVE-2024-7340, published 2024-07-31 (805 days ago)

Source: OSV.dev, checked 2026-10-14. How this is measured.

Weave replaces

Health badge

Maintain Weave? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 86 · excellent

Markdown
[![SelfHostIndex health score for Weave](https://selfhostindex.com/badge/weave-wandb.svg)](https://selfhostindex.com/app/weave-wandb/)
HTML
<a href="https://selfhostindex.com/app/weave-wandb/"><img src="https://selfhostindex.com/badge/weave-wandb.svg" alt="SelfHostIndex health score for Weave"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/weave-wandb.svg
   :alt: SelfHostIndex health score for Weave
   :target: https://selfhostindex.com/app/weave-wandb/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare Weave

8 head-to-head comparisons.

Similar self-hosted ai apps