#1 Persistent memory for AI coding agents based on real-world benchmarks
Repository Index
57,138 visible repositories in the index
1–9 of 9 · Most stars
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
- data-format
- llm
- serialization
- tokenization
Shopify Excel Ledger intelligence platform with dark aesthetic, multi-sheet workbook analysis, 7 departmental dashboards, and live comparative benchmarking.
html emails and attachments to any smtp server with nodejs
A local plugin for image-heavy chats in Codex, Claude Code and other agents: earlier images stop going out with every message, and the model fetches the one it needs by its ID, also after compaction.
- codex
- codex-plugin
- context-management
- developer-tools
Your coding agent paints pixel art in the Aseprite window you already have open. MCP server + skills for Claude Code, omp, Codex, Gemini CLI and Cursor — draws, looks at its work, animates and exports. Gallery and benchmark: pixeli.pebbly.space
- ai-agents
- aseprite
- claude-code
- gamedev
Automated Chrome tracing for benchmarking.
- benchmark
- chrome
Feel how fast a local LLM runs before you buy the hardware
Benchmark recording of an ember app with running with 2 versions of Ember.