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.
@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.
Congrats on the launch, we created a service that has both x402 calls and non-x402 calls (mcp, api). The non-x402 calls are credit based. I'm trying to understand the advantage of using AUDR versus not using it (problem it solves for us). Thanks, in advance!!
Its really nice to see older companies adapt to the AI age. Looking forward to using this!
does the shared run ID handle the nested case - one agent's run calling out to a second agent on a completely different harness, where the second system doesn't know or care about AUDR? trying to figure out if that shows up as two unlinked runs or if there's a parent/child convention for that handoff. we route calls through a few different vendors at Dial and attributing cost across a handoff like that is the part I haven't seen a clean answer for yet
love it, observability becomes more important with scale, something simple like this was definitely missing.
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
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.
rejecting conflicting records seems safer than silently picking a cost. when a router reports usage before the provider's final bill arrives, how do you tie the correction back without counting the run twice?
looks super sharp. how is the migration process for existing subscribers?
does it support automatic usage warnings before a user hits their monthly limit?
pricing for AI apps is moving so fast right now, flexible tiers are definitely needed.
An open standard for tracking who started an agent run and what it cost across every system it touched is the kind of plumbing this space needs before billing can be trusted, and borrowing the call detail record idea is a smart frame. A shared run ID minted by the harness is the crucial part. Curious how quickly other harnesses have picked up the schema.
Can we plug this into our existing stripe account or do we have to migrate everything over?
usage based billing is such a headache to build from scratch. glad someone simplified this.
The Call Detail Record parallel is spot on. Telecom figured out decades ago that you don't need one switch to see the whole call. Also love how precisely scoped this is against what already exists, that it sits on top of OTel's Gen AI conventions rather than competing with them, and it's explicitly the upstream half of FOCUS. Excited to see where this goes, especially with more teams starting to run multi agent stacks where the fragmentation can only get worse.
Excited about this launch, which helps make AI consumption explainable and not just measurable.
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.
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.
Hadn’t thought about this problem before but I can see why it’s coming up now.
About AUDR by Chargebee on Product Hunt
“Open standard for tracking agent run costs”
AUDR by Chargebee launched on Product Hunt on October 6th, 2026 and earned 335 upvotes and 55 comments, earning #3 Product of the Day. 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.
AUDR by Chargebee was featured in Open Source (68.9k followers), Developer Tools (521.1k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 136.3k products, making this a competitive space to launch in.
Who hunted AUDR by Chargebee?
AUDR by Chargebee was hunted by fmerian. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how AUDR by Chargebee stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
fmerian
@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