Oodle.ai
$10 per million agent traces
Details
- External ID
- 48907615
- Source
- HN
- Company
- —
- Product
- Oodle.ai
- Website domain
- oodle.ai
- Launched
- July 14, 2026
- Cohort
- —
- Upvotes
- 31
- Upvotes percentile
- 0.7885304659498208
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
Hi HN, we're Kiran and Vijay!Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability.Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS Lambda.Since we process each span of every trace, instead of running LLM-based evals on each, we first analyze them using deterministic techniques. We detect tool failures, retries, loops, abnormal token usage, latency regressions, schema violations, sentiment, and other production signals. We've written more about the approach here: https://blog.oodle.ai/you-cant-sample-your-way-to-reliable-a...The combination of our own engine, no sampling, and deterministic processing before LLM-for-evals allows us to price at $10 per million traces, provide sub-second p99 query latency, and have healthy margins. Before building this, we used Langfuse for our own agent observability, which was 6x more expensive.Still super early, and rough around some edges, we would love your questions and feedback!
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- B2B
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- agent trace logging and analysis
- Manually corrected
- False
Could you build this?
No Building a petabyte-scale, S3-native columnar database and unified observability engine that operates at high throughput and sub-second query latency requires world-class database systems expertise.
What it would actually take: The architecture requires a custom distributed columnar storage engine (likely in Rust, C++, or Go) parsing Parquet or custom formats directly over object storage (S3), complete with a vectorized query engine, PromQL parser, and distributed indexer. The hardest parts are zero-disk serverless query caching, compaction algorithms, and managing multi-tenant ingest pipelines at hundreds of gigabytes per second. This necessitates a team of veteran distributed database and systems engineers.
Discussion
12 comments analyzed.
Competitors mentioned: Telemetry Pipeline for AI-Era Data Volumes (seller on competitor domain), Traditional APM vendors, Parquet format solutions
Concerns raised: Pricing expensive at $10/million spans vs $0.75/million through other vendors, Name collision with Oodle compression library causes confusion, Parquet format limitations for metrics storage
Feature requests: Automatically surface agent failures, Share vendor capabilities and pricing page
Competitors
Other products that read as similar to this one — 429 launches clear the similarity bar, closest 8 shown.
Attention rank: #97 of 430 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 253 days after the earliest competitor.
- AI Observability by OpenObserve · ph · 2026-09-10 · 304 upvotes · similarity 0.55
- Oodle · hn · 2025-11-04 · 11 upvotes · similarity 0.54
- 83 browser-use trajectories, visualized · hn · 2026-01-23 · 7 upvotes · similarity 0.53
- We instrumented Claude Agent SDK using a tiny Rust proxy · hn · 2025-12-04 · 6 upvotes · similarity 0.50
- Torrix, self hosted, LLM Observability,(no Postgres, no Redis) · hn · 2026-05-13 · 74 upvotes · similarity 0.49
- LLM agents that write Python to analyze execution traces at scale · hn · 2026-03-07 · 5 upvotes · similarity 0.49
- agentic-kv-cache · github · 2026-09-10 · 22 upvotes · similarity 0.48
- BetterDB, MIT Valkey-native context layer for AI agents · hn · 2026-06-26 · 5 upvotes · similarity 0.48
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.