Compile-time-safe dependency injection for Swift without the boilerplate

Long-horizon iOS coding benchmark for autonomous coding agents. Agent-agnostic harness, Tier 1 Atlas PRD, roadmap for Tiers 2-8.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

The agent that grows with you

Smart model router for pi coding agent, multi-signal triage with keyword matching, heuristic analysis, AI fallback, and auto-discovery

Multi-tiered memory and knowledge base plugin for TUI coding assistants (Claude Code, Copilot CLI, OpenCode, Cline, Cursor)

Awesome paper in LLM Psychometrics and LLM Psychology

An AI-chat bot transforming counseling with personalized support and expert assistance.

On-device learned cache eviction for iOS/Swift. RL-based policy (273-param neural network) trained via Belady-inspired rewards. Includes LRU, LFU, FIFO, SIEVE baselines. Built on SwiftGrad/SwiftRL.

Field Theory CLI for bookmarks, Library, commands, and agent workflows

Manipulate Claude Code's 5-hour usage window into resetting when you actually need it.

runs anywhere. uses anything

Real-time dashboard for photographing Northern Lights with Dutch windmills. Live Kp index, OVATION aurora probability, DSCOVR solar wind, cloud forecasts, 24K windmill map with light pollution over…

BT Maaş Endeksi - Türkiye yazılım sektörü maaş raporu. Bağımsız ve açık kaynak.

Fast, accurate & comprehensive text measurement & layout

An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.

better claude harness

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

Hindsight: Agent Memory That Learns

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Control your claude code from your apple watch

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

Examples in the MLX framework

MLX: An array framework for Apple silicon

Karpathy's autoresearch adapted for iOS cold launch optimization — 5 frontier AI models, 117 experiments, 558ms → 189ms (-66%)

AI-driven architecture optimization of a Swift SPM project — 461→76 score in 27 autonomous experiments

Native macOS App Store Connect tool with MCP. Submit iOS apps to App Store with AI agents

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.

A curated list of awesome iOS ecosystem, including Objective-C and Swift Projects