Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Open-source version of Anthropic's internal analytics engine

Details

External ID
48463102
Source
HN
Company
—
Product
Open-source version of Anthropic's internal analytics engine
Website domain
github.com
Launched
June 9, 2026
Cohort
—
Upvotes
15
Upvotes percentile
0.703551912568306
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

Hey HN, here's the repo if you'd like to try it out: https://github.com/Kaelio/ktxBlog post here: https://www.kaelio.com/blog/open-source-anthropic-internal-d...Would love your feedback.

Enrichment

Theme
interactive simulations and creative experiments
Vertical
Horizontal
Function
Analytics & BI
Audience
Developer
AI stance
Not AI
Project type
Hobby / open-source project
Normalized one-liner
open-source analytics engine
Manually corrected
False

Could you build this?

Partial Building an analytical query engine or visualization layer is manageable, but replicating a high-throughput internal analytics engine for LLM trace logs at scale requires sophisticated distributed streaming and OLAP database design.

What it would actually take: A full-scale internal LLM analytics engine needs an OLAP backend like ClickHouse or DuckDB tuned for high-cardinality JSON spans and token usage metrics. The pipeline requires high-throughput ingest via Apache Arrow or Kafka, columnar storage compaction, and efficient query planners for custom aggregation over massive token sequences. Developing it demands systems engineering expertise in columnar databases and telemetry streaming.

Discussion

2 comments analyzed.

Concerns raised: Difficulty specifying analytics questions in natural language without statistics expertise, Garden of forking paths problem makes analytics specification ambiguous, Questionable claim that analytics has single correct answer unlike code

Competitors

Other products that read as similar to this one — 35 launches clear the similarity bar, closest 8 shown.

Attention rank: #15 of 36 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 223 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a analytics & bi tool for Legal yet.