# Chengjun023/agent-smith

> A local Codex model router with a native macOS floating usage monitor and reproducible benchmarks: routine work goes to cheaper models, hard cases to expensive ones.

- Magnitude: 3.8 out of 10 — Early signal
- Stars: 103 total · +4 stars measured 2026-10-05, 10:59–12:34 UTC, ≈ 22 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-09-30 · Last push: 2026-10-01
- GitHub: https://github.com/Chengjun023/agent-smith · Page: https://gitnova.dev/en/r/Chengjun023/agent-smith

## Useful for

- Run Codex task routing via the adaptive-router plugin to cut token spend
- Track token usage and reference cost in the Codex Float floating window
- Run the offline demo benchmark to compare routing strategy costs

## Why it’s here

- Star-counter measurements on 2026-10-05 (UTC), 10:59–12:34: 99 → 103 stars (+4). This is the change over that interval.
- Estimated end-of-day forecast: about +22 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 103 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #126.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 2
- Average over the last week: 18 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 9 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-05: 0, 0, 0, 1, 1, 0, 12, 71, 4

## Spotted in now

- Top new repositories this week: #126

## More in this category

1. **lexmount/moli** — 8.3 · Breakout · AI agents · Rust · +1,053 stars measured 2026-10-05, 00:06–12:33 UTC, ≈ 1,894 by evening
   Moli is a headless browser written in Rust for AI agents, combining a full browser runtime with on-demand layout and rendering to keep resource use low. It fetches and extracts web pages, searches the web, and automates browser tasks via…
   Full card: https://gitnova.dev/en/r/lexmount/moli.md
2. **QingYunA/answer-me-with-html** — 7.2 · Early signal · AI agents · JavaScript · +281 stars measured 2026-10-05, 00:06–12:33 UTC, ≈ 549 by evening
   An agent skill that turns an AI agent's answers to hard questions into a one-page HTML with diagrams and tables instead of a wall of text. The model writes only a Markdown draft, and the skill's CLI renders the page.
   Full card: https://gitnova.dev/en/r/QingYunA/answer-me-with-html.md
3. **pingdotgg/t3code** — 7.1 · Breakout · AI agents · TypeScript · +246 stars measured 2026-10-05, 00:06–12:32 UTC, ≈ 472 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
4. **thedotmack/claude-mem** — 7.0 · Breakout · AI agents · TypeScript · +255 stars measured 2026-10-05, 00:06–12:32 UTC, ≈ 499 by evening
   Persistent memory system for Claude Code and other agents: it captures agent actions via lifecycle hooks, compresses them into semantic summaries, and injects relevant context into future sessions.
   Full card: https://gitnova.dev/en/r/thedotmack/claude-mem.md
5. **CopilotKit/OpenDots** — 6.9 · Peaking · AI agents · TypeScript · +230 stars measured 2026-10-05, 00:06–12:32 UTC, ≈ 469 by evening
   An open-source template for always-on AI agents (Dots) with their own computer, working across web chat, calls, and Slack. Lets you build a self-hosted workspace with documents, review, and tools.
   Full card: https://gitnova.dev/en/r/CopilotKit/OpenDots.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-05 12:40 UTC, updated every 30 minutes.