← Browse tools

Observability & evaluation

Weights & Biases Weave

Application traces and versioned evaluation workflows integrated with the Weights & Biases platform.

Overview

Research summary

Weave by Weights & Biases records inputs, outputs and nested calls from generative AI applications and connects them with datasets and evaluation results. Developers instrument functions, define scoring routines and compare experiments to understand how changes affect application quality and behavior. The public repository contains the Apache-2.0 toolkit, primarily implemented in Python, while the associated Weights & Biases platform provides hosted collaboration and operational workflows under separate terms.

Weave is focused on LLM and agent application development; it is distinct from the broader W&B Models offering for model training and experiment tracking.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services available

The provider offers paid products or services. Free options may also be available.

View pricing & services ↗

Commercial offering checked 2026-10-02.

Licence scope

Toolkit:Apache-2.0Hosted service:Proprietary

Implementation

Recorded implementation details and interfaces for Weights & Biases Weave.

Implementation details

Python-first tracing and evaluation toolkit connected to a hosted web platform.

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Toolkit:Apache-2.0Hosted service:Proprietary

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

wandb/weave ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 6

Research metadata

Research date
2026-10-01
Catalogue snapshot
2026-10-06

Community & social 1 channels

Video