AUDR by Chargebee - Open standard for tracking agent run costs
by•
AUDR (Agent Usage Detail Record) is an open standard, for capturing who initiated an agent run and what it cost across every system that run touches. Inspired by the telecom industry's Call Detail Record, AUDR defines a common JSON schema that any harness, router, or billing system can emit and ingest. Three core rules make it work: a shared run ID minted by the harness, clear field ownership, and strict merge rules where conflicts are rejected and corrections are new records.
Replies
@Chargebee pioneered the SaaS industry (first launched here in 2014), and so they do in the AI economy.
Agents call tools, hit APIs, even pay per request with products like pay.sh by @Solana Foundation. AUDR (Agent Usage Detail Record) is the logical next step, and it's open. @Chargebee pushed the initial commit, adopted by @Mastra, @Merge, and more.
Star this repo: github.com/openaudr/audr
@fmerian thanks so much, Flo! Excited about this launch. There's a huge need for a standard way to track agent costs and usage. We're grateful for early reviewers and advocates who have contributed thus far. Big shout out to @Merge , @Mastra, and @OpenHuman teams.
Hi PH community, we’re really excited to launch AUDR.
The telecom industry has always had a standard, carrier-agnostic way of recording usage for each call. Today’s long-horizon agents need a similar standard that works across model routers, gateways, agent frameworks, and the wider AI stack. AUDR (Agent Usage Detail Record) is an open standard specification for recording agent usage and costs in granular detail.
At Chargebee, we help scale monetization for some of the fastest growing AI startups and enterprises. And one thing they all have in common is a granular understanding of AI costs. That understanding informs how creatively and sustainably they price. Whether it’s charging for active agent minutes, resolved outcomes, or an extremely hybrid model, they all share a deep grounding in tokenomics. AUDR is built to enable the same depth for everyone.
We’re thankful to teams at @Merge, @Mastra, and @openhumanfor their early reviews and contributions. We’ve already shipped adapters for NVIDIA NeMo Relay, Merge Gateway, Mastra, Vercel’s AI SDK, and LiteLLM.
Help us improve it at openaudr.dev
@cbkrish S/O for this new launch! psyched to see @Chargebee back on @Product Hunt. looking forward to what's next.
Thank you everyone for the love and ideas to take this further. We are launching AUDR along with an initial set of adapters to get you'll going. We'd love for you to co-build adapters or share what you want us building out next.
Nemo Relay: https://github.com/openaudr/audr/tree/main/adapters/nemo-relay
LiteLLM: https://github.com/openaudr/audr/tree/main/adapters/litellm
Merge Gateway: https://github.com/openaudr/audr/tree/main/adapters/merge-gateway
Vercel SDK: https://github.com/openaudr/audr/tree/main/adapters/vercel-ai
Mastra: https://github.com/openaudr/audr/tree/main/adapters/mastra
Lago Sink: https://github.com/openaudr/audr/tree/main/sinks/lago
Chargebee Sink: https://github.com/openaudr/audr/tree/main/sinks/chargebee
lfg! and anyone can request more adapters by creating an issue here: github.com/openaudr/audr/issues
Observability for Agents is a big deal these days. It is something many organizations are trying to solve for but the solutions are limited. This looks pretty cool
Thanks, we're excited too! Observability shows what happened in a run. AUDR adds who it was for and what it cost.
A very important problem to address - Most teams I talk to build their own dashboards consolidating cost data from multiple sources but still don't get a clear picture of the actual cost to serve a customer. Knowing which cohort of customers is the most (or least) profitable can help make a lot of decisions in the product/GTM.
Excited about this launch, which helps make AI consumption explainable and not just measurable.
@sukanya_kuppuswamy thanks Sukanya! That's a fine way to sum up what AUDR can enable.
@mrakashsharma framing this
Great to see this live!
@astharattan likewise! what excites you the most about this launch?
@fmerian Love the standard it is proposing, would make things much simpler for teams.
@astharattan oss ftw!!
@sidhdharth thank you so much. Do join in adopting this framework and give us your feedback on making it better. here's the Git link
love it, observability becomes more important with scale, something simple like this was definitely missing.
@inferense thank you. Do let us know if you'd like any support from our end in adopting this framework.
Its really nice to see older companies adapt to the AI age. Looking forward to using this!