Langfuse
Helicone AI
LangSmith
LangChain
PromptLayer
Braintrust.dev
Humanloop
Openlayer
Threadfall
World Anvil
Kanka.io
Obsidian Portal
Obsidian.md
LegendKeeper
Scabard
Notion
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.
Threadfall is a campaign management platform built for live tabletop role-playing games. It records the session, transcribes speech in real time with speaker diarization, and turns the resulting transcript into a recap, a running campaign codex, and a live screen for the table โ so the Game Master can stop taking notes and focus on running the game.
What it does at the table. During a live session, Threadfall captures audio, transcribes it in real time using state-of-the-art automatic speech recognition, and identifies who is speaking. A live screen โ designed for a second monitor, a tablet at the table, or a shared display โ shows the unfolding session in a clean, distraction-free view. The Game Master sees recent dialogue, current scene context, and tracked entities without breaking flow.
What it does between sessions. When the session ends, Threadfall produces a recap that captures what actually happened โ character actions, key dialogue, decisions, and consequences โ drawn from the transcript rather than from the GM's memory. It updates the Living Codex: a structured repository of characters, locations, factions, items, and plot threads that grows automatically as the campaign progresses. Entities are extracted, relationships are mapped, and the codex is searchable from the next session onward.
Who it's for. Game Masters running ongoing campaigns โ particularly online or hybrid groups using voice chat, but equally useful for in-person tables with a recording device. It's system-agnostic: nothing in the product assumes Dungeons & Dragons or any specific rule set. It's been built and tested against D&D 5e and 5.24, but works equally well for Pathfinder, Call of Cthulhu, indie systems, and anything else where a group of people talks for hours and the GM has to remember it all.
Free tier. New users get two complete live sessions and recaps to try the product, with no credit card required.
Try Threadfall at thread-fall.com.
Langfuse ThreadfallNo Threadfall videos yet. You could help us improve this page by suggesting one.
Threadfall's answer:
Threadfall is the only campaign management tool built around the live session itself. Other tools โ World Anvil, LegendKeeper, Kanka โ expect the Game Master to type everything into a wiki between games. Threadfall flips that: it records the session, transcribes it in real time with speaker diarization, and extracts the campaign data automatically. The recap is ready before everyone's packed up, and the Living Codex of NPCs, locations, and plot threads updates itself as the campaign runs.
The differentiator is the architecture: most TTRPG tools are wikis with rules; Threadfall is a real-time audio pipeline plus a knowledge graph, with the wiki as an output rather than an input.
Threadfall's answer:
Because the work of running a campaign is mostly record-keeping, and no other tool actually removes that work โ they just give you nicer places to do it.
Manual campaign wikis (World Anvil, LegendKeeper, Kanka, Notion) require hours of upkeep between sessions. The GM is rewarded for diligence, punished for forgetting. Threadfall removes the upkeep entirely: the session is the source of truth, and the tool extracts what matters automatically.
For GMs who would rather spend their prep time on scene design and player engagement than transcribing what happened last week, the choice is straightforward. For GMs who enjoy maintaining elaborate wikis as a creative outlet, the existing tools are fine โ Threadfall isn't trying to replace that workflow.
Threadfall's answer:
Game Masters running ongoing tabletop RPG campaigns โ primarily Dungeons & Dragons 5e and 5.24, but the product is system-agnostic and works equally well for Pathfinder, Call of Cthulhu, and any other system. The core user is running a campaign that's lasted more than a few sessions, has accumulated NPCs and plot threads, and is starting to feel the weight of record-keeping.
Online and hybrid groups (Discord voice, Foundry VTT, Roll20) get the most direct benefit because audio capture is already part of their setup. In-person tables work too with a recording device on the table.
The audience skews experienced โ newer GMs running their first short campaign typically don't yet feel the record-keeping pain that Threadfall solves.
Threadfall's answer:
Threadfall was built by a Game Master who kept losing the thread between sessions โ which NPC made what promise, where the party left off, who was holding the cursed dagger. Note-taking didn't fix it; writing during the game pulled focus away from running it. The product was built to remove the choice between being present at the table and remembering what happened there.
It launched in May 2026 and is in active development. The founding group of GMs using it weekly provides direct feedback, and updates ship as that feedback comes in.
Threadfall's answer:
Backend: Python, FastAPI Database: PostgreSQL (Neon) Frontend: JavaScript, WebSocket streaming for live session view AI / NLP: Large language model integration for recap generation, entity extraction, and codex maintenance
Based on our record, Langfuse seems to be more popular. It has been mentiond 29 times since March 2021. 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.
Langfuse and LangSmith exist for this. Use them. The 30 minutes you spend setting up observability saves you the 87 hours you'd spend debugging blind. - Source: dev.to / 5 days ago
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 / 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
Helicone AI - Open-source LLM Observability for Developers
World Anvil - World Anvil is a worldbuilding tool for Authors, Storytellers and worldbuilding lovers.
LangSmith - Build and deploy LLM applications with confidence
Kanka.io - Kanka.
LangChain - Framework for building applications with LLMs through composability
Obsidian Portal - Obsidian Portal takes the pain out of managing your tabletop RPG
