Vellum
Vellum is a developer platform for building, testing, and deploying large language model applications in production environments.
About this data
Updated June 22, 2026
Overall Pulse Score
-7 over this period
A 0-100 index summarizing the tone of 107 relevant public mentions gathered from public online communities across 12 weeks in the selected period. It measures online sentiment, not a rating of the product's quality.
Weekly Sentiment Trend
Pulse Score by week over the selected period. Each point is one complete week of mentions.
This week in public discussion
Discussion around Vellum over the recent period leaned negative, with bugs and reliability problems accounting for the majority of mentions. Commenters flagged issues including HTTP 500 errors from the managed Gemini embeddings backend and contrast failures in shipped UI surfaces. A smaller number of posts touched on feature praise and new releases, with several mentions highlighting interest in a no-code eval builder. Overall sentiment remained close to the prior period, with complaints outweighing positive feedback by a wide margin.
AI-generated summary of public online discussion during this period. It reflects the tone of that discussion, not facts about the product or our views.
Sentiment mix by week
How the tone of public discussion splits each week.
Most-discussed praise
Most-discussed complaints
Themes across the selected period, with mention counts.
Sample public mentions
Showing 5 of 107 analyzed public mentions in this period, with links to the original source. We do not reproduce full threads.
“Conversion and support for Vellum package manager. Hey there! I love and daily a number of these hacks, but sadly this rmhacks project is incompatible with the bettertoc hack within Vellum. I'm currently struggling since the hacks I use in your project are not ones that are incom...”
“Failed to install qemu-user-static using apt-get!. Downloading packages via reManager... Downloading alpine-chroot-install (1/2)... Transferring alpine-chroot-install (1/2)... Downloading alpine-chroot (2/2)... Transferring alpine-chroot (2/2)... Installing packages... Installing...”
“App design-system CSS (.v-* classes / --v-* tokens) is not injected into web-client app iframes — multi-file apps render unstyled. ## Summary The app-builder skill tells the model the design-system CSS and .v-* widget classes are **auto-injected** into every app, so generated app...”
“Installation on remarkable 2 - documentation is a bit short. So I have followed the installation steps in the documentation: Install Vellum vellum install koreader I did that, but now what? How do I launch koreader? Searching around, I found that I might need a "launcher", and ap...”
“How to start an application?. Alright, I installed koreader and appload using vellum. Now, the README states: To put new apps on the tablet, place their directories in /home/root/xovi/exthome/appload/. I have verified that this is the case: To start an application as a window, lo...”
152+ more analyzed mentions, full history, and theme breakdowns are part of Pro.
Get ProDeeper analysis
- Bugs and reliability complaints dominated discussion volume by a wide margin, setting a frustrated baseline tone across the window.
- Sentiment followed a volatile path, with a sharp mid-window drop followed by a partial recovery that still left the overall score slightly below where the period started.
- Opinion was most divided between commenters excited about feature direction and roadmap ambition versus those anchored to unresolved technical failures.
- UI and accessibility critiques added a secondary layer of concern, with several mentions suggesting interface quality issues compounded reliability frustrations.
| Praise theme | Mentions |
|---|---|
| Strong features | 12 |
| Feature requests | 7 |
| New releases | 5 |
| Polished UI | 3 |
| Good integrations | 3 |
| Complaint theme | Mentions |
|---|---|
| Bugs | 40 |
| Reliability | 25 |
| Missing features | 18 |
| Feature requests | 12 |
| UI frustrations | 7 |
Discussion around Vellum over the past four weeks has been dominated by a persistent undercurrent of frustration, with bugs and reliability issues accounting for the largest share of complaint-themed mentions by a significant margin. Commenters flagged a range of technical failures, with several mentions pointing to backend errors such as HTTP 500 responses disrupting core functionality at startup, as well as installation failures and missing package metadata. These reports gave the overall tone a quality of accumulated disappointment rather than isolated incidents, suggesting that reliability concerns have been a steady presence throughout the window rather than a single flashpoint.
The score trajectory tells a volatile story. Discussion opened the window at a modest level, then dropped sharply in early May before recovering. A particularly steep decline appeared in the June 1 data point, where sentiment fell to its lowest reading in the window across a small but notable cluster of mentions. That low was followed by a rebound in the June 8 period, though the most recent reading settled back into the mid-forties range, leaving overall sentiment slightly below where the window began. This pattern of sharp dips and partial recoveries suggests that negative news arrives in concentrated bursts and temporarily drags tone down before discussion rebalances.
On the more constructive side, feature praise and feature requests together made up a meaningful portion of the positive signal, with commenters expressing interest in new agent integrations and no-code workflow tooling. Several mentions reflected genuine enthusiasm for product direction, particularly around canvas-style evaluation authoring. Opinion was divided most visibly along the line of promise versus execution, with some commenters engaging eagerly with roadmap ideas while others remained anchored to unresolved technical complaints.
UI concerns, though a smaller theme by count, added texture to the critique, with discussion suggesting that interface hierarchy and accessibility contrast failures were adding friction. The presence of accessibility-related complaints alongside reliability issues points to a perception that surface-level polish and underlying stability are both under pressure at the same time.
AI-generated summary of public online discussion during this period. It reflects the tone of that discussion, not facts about the product or our views.
Member perspectives
Individual opinions from Pro members, posted over time. These are personal member views, not aggregated sentiment data.
Overall Pulse Score
-7 over this period
A 0-100 index summarizing the tone of 107 relevant public mentions gathered from public online communities across 12 weeks in the selected period. It measures online sentiment, not a rating of the product's quality.
Data summary
Compare with another tool
Vellum
41
Koala AI
81
Score-level preview from live weekly tracking.
Are you Vellum?
If you represent this product, you can share context about the data shown here. We read every submission.
Share feedbackAffiliate disclosure
Some links on this site may be affiliate links. If you click one and make a purchase, we may earn a commission at no extra cost to you. Learn more.
Compare with similar tools
RevenueCat
A platform that manages in-app purchases, subscriptions, and revenue analytics for iOS and Android app developers.
Free tier; paid plans available
View DetailsCodemirror
An open-source JavaScript code editor component for browsers, used by developers building web-based text and code editing interfaces.
Free
View Details