Lists (5)
Sort Name ascending (A-Z)
Starred repositories
Multi-tier framework for evaluating AI agent skills and plugins with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how …
Bondy Connect is an open source, always-on and scalable application networking platform connecting all elements of a distributed application—offering service and event mesh capabilities combined. B…
diro5t / auto-ontology
Forked from NVIDIA/auto-ontologyAuto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.
Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states and actions.
A resource for learning the OTP framework with the Gleam programming language
A modern, typed Lisp for ECMAScript, the browser, and the Deno JavaScript runtime
Datomic + Cozodb but waaaaaaaay better. Datalog for BEAM
An experiment in a statically typed LFE with algebraic data types
A Julia Package for Active Inference
A persistent runtime for long-lived LLM agents
Pure Gleam tensor library with quantization (INT8, NF4, AWQ), Flash Attention, and 2:4 Sparsity - 7.5x memory multiplication
Open Policy Agent (OPA) is an open source, general-purpose policy engine.
⭐️ A friendly language for building type-safe, scalable systems!
Zygo is a Lisp interpreter written in 100% Go. Central use case: dynamically compose Go struct trees in a zygo script, then invoke compiled Go functions on those trees. Makes Go reflection easy.
Pure Go R7RS Scheme — embeddable interpreter with hygienic macros, first-class continuations, and sandboxing