AI Developer Tool · Python

Enclosure

A scriptable completely deterministic LLM testing harness, complete simulated enfironment

jerry howell@openconstruct · Atlas 64.1 · #14= builder

View on GitHub1 Open jerry howell's Atlas

What it is

Enclosure is a behavioral scenario harness for evaluating AI models' tool use and interactive behavior in controlled, reproducible environments using simulated tools and scripted agents.

Scored atc3a91057 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

NLP & LLMs80%
AI Agents70%
Machine Learning60%
MLOps40%
Computer Vision10%
Data Science10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

07RegesMoEML Application · C++RegesMoE is an end-to-end application that enables running the RegesCore 35B mixture-of-experts model on a normal PC with a single GPU, providing an installer, local OpenAI- and Anthropic-compatible API, and web app.72.5/100AdvancedMaster MindNLP & LLMs
08WebsearchRAG System · PythonThe Websearch repository provides a Dockerized, local-first web search service that integrates with LM Studio via the Model Context Protocol (MCP). It offers tools for web search, reading webpages, extracting information, mapping sites, crawling, and deep research, all with…70.9/100AdvancedJens MittelbachNLP & LLMs
09EnclosureAI Developer Tool · Python70.7/100Advancedjerry howellNLP & LLMs
10tinymarsArchitecture Modification / Research · PythontinyMARS is a research project investigating proprioceptive channels as an architectural input for language models, implemented both as an adapter to a frozen LLM and as a from-scratch native model. It includes training code, evaluation scripts, and extensive documentation…69.6/100AdvancedMario GutierrezNLP & LLMs
11Fresta-DiamondLibrary / Framework · PythonFresta Diamond is a Python runtime library that provides typed contracts, persistent state management, and explicit effect controls for LLM-based applications, featuring module admission, attention continuation, and cognitive architecture concepts.69.4/100AdvancedTiago SantosNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from jerry howell