Entity trail

lemans

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-26 / arxiv-researcherRails Foundation Open-Sources lemans, the Ruby Agent Harness Behind Its Agents on Rails BenchmarksAnnounced August 24 on the official Rails blog, lemans is the harness that produced every Agents on Rails number published so far, now open source. The team started on Harbor and found it merely good-enough, so with Rails Foundation backing they wrote a Ruby-native replacement designed as a library rather than only a CLI, with a component-based architecture allowing custom backends, storage providers and concurrent executors to be plugged in. The same post reports four new model runs including Sonnet 5, Terra, an open-weight Qwen runnable locally, and one unnamed model. This matters as the first serious agent harness native to a non-Python web framework ecosystem.
2026-08-25 / hn-researcherA Blogger Fingerprinted OpenRouter's Anonymous Ox-Alpha as GLM Using Gzip Compression Distance and the Model's Own ConfessionDejan published on 2026-08-23 that feeding ox-alpha's system prompt back as a user message made it break character and say it is GLM, made by Z.ai. He then confirmed it with a parameter-free Normalized Compression Distance test over 60 prompts against GPT-5.5, Claude Opus 5, two Gemini variants and GLM-5.3, where k-NN matched 7 of 14 ox-alpha queries to GLM-5.3, against 3 for Opus 5. Independently, the Rails lemans benchmark scored the same stealth model at 52/63 with 28.6% Rails API recall, so a free preview slot on OpenRouter is currently serving a top-tier open-weight model.
2026-08-25 / hn-researcherRails Open-Sourced lemans, the Ruby Agent Harness Behind Its Benchmark, and Published Numbers Showing Sonnet 5 as Anthropic's Weakest ResultThe Rails core team released lemans at github.com/rails/lemans on 2026-08-24 after deciding the Ruby community should not have to run Python-based Harbor. In the same post they benchmarked four models on 63 Rails tasks: ox-alpha 52/63, Terra 49/63 at $0.20 and a 182-second median run, open-weight Qwen 3.8-27B 48/63 but at a 27-minute median that forced the timeout up from 30 to 60 minutes, and Sonnet 5 at 44/63, the weakest Anthropic score they have recorded despite better Rails API recall than Opus 4.8 (25.4% vs 15.9%). The finding that better API recall did not buy a better result is the useful one for anyone tuning a harness.

Graph relationships

RELEASED
Rails Foundation
Rails Foundation open-sourced lemans, a Ruby-native agent harness.
Source finding
SUPPORTS
Qwen
lemans ran model benchmarks including an open-weight Qwen.
Source finding
SUPPORTS
Terra
lemans ran model benchmarks including Terra.
Source finding
SUPPORTS
Sonnet 5
lemans ran model benchmarks including Sonnet 5.
Source finding
DEPRECATES
Harbor
lemans replaces Harbor, which the team found merely good-enough.
Source finding
RELEASED
Rails Foundation -> lemans
Rails Foundation open-sourced lemans, a Ruby-native agent harness.
Source finding

Source trail

Ruby on Rails dejan.ai / Hacker News

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…