Langfuse
Helicone AI
LangSmith
LangChain
Braintrust.dev
Portkey
Openlayer
PromptLayer
Patchlog
Changelogfy
Barelog
Changefeed
Changelog.gy
Changeloggy
CHANGELOG.md
Changelogs.gallery
Langfuse is an open-source LLM engineering platform designed to empower developers by providing insights into user interactions with their LLM applications. We offer tools that help developers understand usage patterns, diagnose issues, and improve application performance based on real user data. By integrating seamlessly into existing workflows, Langfuse streamlines the process of monitoring, debugging, and optimizing LLM applications. Our platform's robust documentation and active community support make it easy for developers to leverage Langfuse for enhancing their LLM projects efficiently. Whether you're troubleshooting interactions or iterating on new features, Langfuse is committed to simplifying your LLM development journey.
Patchlog is a drop-in changelog for web apps. You embed one script tag, with no SDK and no npm install, and get an in-app "what's new" widget plus a hosted changelog page and an RSS feed.
The widget renders inside a Shadow DOM, so it never inherits or leaks the host page's CSS, and it behaves the same in React, Vue, Rails or plain HTML.
Other features: scheduled publishing so you can write updates ahead of time and have them post themselves, per-update view and click analytics, light/dark/auto theming with a custom accent colour on Pro, and 2FA on accounts.
Pricing is flat rather than metered on your traffic: free for 1 project and 25 updates, which shows a small "Powered by Patchlog" badge, or $7/month ($60/year) for unlimited projects and updates, badge removal and advanced analytics. Most tools in this category bill per monthly active user, so the bill grows with your app even though writing release notes does not get harder.
What Patchlog does not do: no user segmentation or targeting, no NPS surveys, no roadmaps or feature voting boards, no email digests, and no public API. If you need those, Beamer or Canny is the better fit.
Langfuse PatchlogNo Patchlog videos yet. You could help us improve this page by suggesting one.
Patchlog's answer:
A real free plan with no trial expiry, and a widget that embeds in any web app with two lines of JavaScript. No bloated feature set, no enterprise pricing for a tool that should be simple.
Patchlog's answer:
Most changelog tools charge $29-$60/month for features most small teams never use. Patchlog gives you a working in-app widget, a public SEO-friendly changelog page, full Markdown support, and RSS on the free plan. The Pro plan is $5/month. It covers everything 90% of SaaS products actually need.
Patchlog's answer:
Indie founders, solo developers, and small SaaS teams who want to keep users informed about product updates without paying enterprise prices for it.
Patchlog's answer:
Built out of frustration with the existing options. Every changelog tool was either too expensive, too complex, or offered a "free trial" that expired before you could evaluate it properly. Patchlog started as the tool we wished existed: simple to embed, honest free tier, no fluff.
Patchlog's answer:
Laravel, Vue 3, Inertia.js, Tailwind CSS, MySQL.
Patchlog's answer:
Patchlog is early-stage and does not publicly disclose customer names at this time.
Based on our record, Langfuse seems to be a lot more popular than Patchlog. While we know about 28 links to Langfuse, we've tracked only 2 mentions of Patchlog. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
In this project we will build a Python banking assistant agent using Strands Agents and make it observable and continuously evaluated using Langfuse โ step by step. - Source: dev.to / about 1 month ago
Langfuse is the open-source standard for LLM observability. It traces every LLM interaction โ prompts, completions, latency, token usage, cost โ and provides the tooling to debug, evaluate, and optimize LLM applications in production. Think of it as "Datadog for LLM calls" with a focus on prompt engineering workflows. - Source: dev.to / about 2 months ago
You're monitoring production traffic. You need Langfuse / Phoenix / Helicone / Braintrust for that. Online eval is a different problem class: implicit feedback, drift detection, hallucination rates on your data, not on HellaSwag. - Source: dev.to / 2 months ago
Gateway or proxy attribution. A reverse proxy in front of the model-provider API records the request, computes the cost, and exposes per-customer breakdowns. Open-source options include Helicone, LiteLLM, Langfuse, and OpenLLMetry. Hosted equivalents serve as the AI cost observability layer for teams that want centralized visibility: LangSmith, Datadog LLM Observability, Arize Phoenix. Adds a network hop.... - Source: dev.to / 2 months ago
Same approach works with Langfuse, Phoenix, Braintrust, or your existing OTel pipeline โ the metadata.userId pattern is the universal part. - Source: dev.to / 2 months ago
This is exactly how I built the changelog widget for Patchlog. It is a drop-in "what's new" widget for SaaS products: one script tag, rendered inside a Shadow DOM so it never collides with the host site's CSS, with light, dark, and auto theming that reads the host's CSS variables when you want it to. There is a free tier if you want to see the technique in a shipped product rather than a blog snippet. - Source: dev.to / 22 days ago
I build Patchlog, so the snippet above is my own tool. I'm not going to pretend otherwise. It's early: the free tier is one project and 25 updates, which is genuinely what I run on my own projects. I'm sharing the approach because it's helped me, and if it saves you the afternoon it cost me to think through, great. - Source: dev.to / 23 days ago
Helicone AI - Open-source LLM Observability for Developers
Changelogfy - Changelogfy is an all-in-one platform to collect, organize and manage customer and teammates feedback, prioritize and build a product roadmap, and announce product updates.
LangSmith - Build and deploy LLM applications with confidence
Barelog - Simple way to create a changelog for your product
LangChain - Framework for building applications with LLMs through composability
Changefeed - A beautiful changelog for your product in seconds
