---
title: "Compare earendil-works/pi vs NVIDIA/auto-ontology vs thedotmack/claude-mem vs affaan-m/ECC"
description: "Side-by-side stored star counts, 7/30-day growth and health for up to four tracked GitHub repositories."
last_updated: 2026-11-22T00:44:27.962
canonical: "https://www.gstars.dev/compare"
---

# Compare earendil-works/pi vs NVIDIA/auto-ontology vs thedotmack/claude-mem vs affaan-m/ECC

Source: https://www.gstars.dev/compare?repos=earendil-works%2Fpi,NVIDIA%2Fauto-ontology,thedotmack%2Fclaude-mem,affaan-m%2FECC

## Summary

- affaan-m/ECC has the most stars (308,372), ahead of earendil-works/pi (123,194).
- affaan-m/ECC has the strongest 7-day star growth (+5,172), ahead of thedotmack/claude-mem (+1,726).
- affaan-m/ECC has the highest health score (62/100), ahead of earendil-works/pi (60/100).
- thedotmack/claude-mem has the most recent code push (Nov 21, 2026).

## Side by side

| Repository | Stars | Growth, 7 days | Growth, 30 days | Health | Language | License | Observed | Description |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [earendil-works/pi](https://www.gstars.dev/repo/earendil-works/pi) | 123194 | Unknown | 6209 | 59.95 | TypeScript | MIT | 2026-11-22T00:43:42.384 | AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI |
| [NVIDIA/auto-ontology](https://www.gstars.dev/repo/NVIDIA/auto-ontology) | 13024 | Unknown | Unknown | 34.8 | Python | Apache-2.0 | 2026-11-16T00:47:13.332 | Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context ret |
| [thedotmack/claude-mem](https://www.gstars.dev/repo/thedotmack/claude-mem) | 118848 | 1726 | 16508 | 35 | TypeScript | Apache-2.0 | 2026-11-22T00:44:27.962 | Persistent Context Across Sessions for Every Agent –  Captures everything your agent does during sessions, compresses it with AI, and injects relevant context b |
| [affaan-m/ECC](https://www.gstars.dev/repo/affaan-m/ECC) | 308372 | 5172 | 21825 | 62.21 | JavaScript | MIT | 2026-11-22T00:43:30.531 | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor  |

Null/unknown means unavailable or unmeasured, not zero. Definitions: https://www.gstars.dev/methodology

## Sitemap

- [Sitemap](https://www.gstars.dev/sitemap.md)
- [llms.txt](https://www.gstars.dev/llms.txt)
