HarnessMM: recursive self-improvement for harness token efficiency
- agent-harness
- llm-agents
- recursive-self-improvement
- token-efficiency
132,183 visible repositories in the index
2,785–2,808 of 3,135 · Most stars
HarnessMM: recursive self-improvement for harness token efficiency
Fast and storage-efficient spatial database engine for OpenStreetMap data
PyTorch Connectomics: segmentation toolbox for EM connectomics
Components for interactive scientific writing, reactive documents and explorable explanations.
MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
Solutions to In-Class questions, Problem Sets and Exams of MIT Mathematics for Computer Science 2015 (same as 2019 Open Learning Library)
Practical volume computation and sampling in high dimensions
ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.
Expertiza is a web application through which students can submit and peer-review learning objects (articles, code, web sites, etc). The Expertiza project is supported by the National Science Foundation.
Flake for packaging, building and running Zig projects.
A lightweight, simple FTP server. Pure Java, no dependencies.
scPerturb: A resource and a python/R tool for single-cell perturbation data
A Python interface to access neuroanatomical atlases
A curation of resources, projects, and communities related to permacomputing.
Turn repository maintenance into an actionable plan. Local-first CLI + browser workbench for docs, testing gaps, change impact and CI readiness. Zero dependencies.
Agent Skill for editable scientific figures in Adobe Illustrator from ideas and references. Supports sequential element-by-element drawing, optional multi-cursor swarm presentations, and native gradients via Python, Windows COM and ExtendScript.
This repository provides a set of tools and libraries to integrate Intel® OpenVINO™ Toolkit with ROS 2 (Robot Operating System), enabling efficient deployment of deep learning models for computer vision applications on Intel® hardware.
An expansible unit conversion library for .NET: exact definitions, synonym-based unit names and no dependencies.
Eleven ordinary UI controls drawn as rubber-hose cartoon characters. One file each, no dependencies.
Install, upgrade and uninstall Elm dependencies
Manage AWS organizations, organizational units (OU), accounts and service control policies (SCP).
Utilities for reasoning about musical notes, frequencies, and intervals
Ultra-Efficient Humanoid Control with Differentiable Simulation.
ChemML is a machine learning and informatics program suite for the chemical and materials sciences.