# amontlabs/lcu

> LCU exposes Codex's original computer-use runtime to any agent harness, letting agents control desktop apps and Chrome tabs without logging into Codex. Includes adapters for Pi, Codex CLI, and Claude Code.

- Magnitude: 4.8 out of 10 — Breakout
- Stars: 1,649 total · +27 stars measured 2026-10-20, 05:14–06:37 UTC, ≈ 286 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-09-22 · Last push: 2026-10-19
- GitHub: https://github.com/amontlabs/lcu · Homepage: https://lcu.amontlabs.com · Page: https://gitnova.dev/en/r/amontlabs/lcu

## Useful for

- Let a Claude Code agent click and type in desktop apps like Zed or Notes
- Control Chrome tabs through the official extension with per-site approval
- Run LCU on an unattended VM with pre-approved tools for automation

## Why it’s here

- Star-counter measurements on 2026-10-20 (UTC), 05:14–06:37: 1622 → 1649 stars (+27). This is the change over that interval.
- Estimated end-of-day forecast: about +286 stars, using observed gains and the previous day.
- Over the last two days the pace is 8.3× that of the previous week and a half.
- The repository is 28 days old and already has 1,649 stars.
- Top new repositories this month: #98.
- About 31 forks a day — people are taking the code.

## 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: 92
- Issues and pull requests: 45
- Watchers: 4
- Average over the last week: 122 per day
- Usual pace: 61 per day
- Stars in the last hour (measured): 19
- Latest release: v0.11.6 (2026-10-19)

## Stars per day, last 29 days (oldest → newest, today is partial)

2026-09-22 … 2026-10-20: 0, 0, 0, 0, 0, 3, 3, 0, 0, 0, 0, 9, 236, 288, 129, 75, 83, 40, 17, 60, 105, 31, 18, 33, 18, 19, 18, 469, 27

## Spotted in now

- Top new repositories this month: #98

## More in this category

1. **google-research/harness2** — 9.7 · Breakout · AI agents · Python · +1,074 stars measured 2026-10-20, 00:22–06:36 UTC, ≈ 4,283 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **MadsLorentzen/ai-job-search** — 9.3 · Breakout · AI agents · Python · +984 stars measured 2026-10-20, 00:22–06:36 UTC, ≈ 3,719 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/MadsLorentzen/ai-job-search.md
3. **anomalyco/opencode** — 7.8 · Breakout · AI agents · TypeScript · +301 stars measured 2026-10-20, 00:22–06:36 UTC, ≈ 1,162 by evening
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
4. **IsuruMaduranga/harness-engineering-101** — 7.4 · Early signal · AI agents · Python · +61 stars measured 2026-10-20, 00:22–06:36 UTC, ≈ 266 by evening
   A book series explaining how to build AI agents from first principles, treating the LLM as a stateless brain and the harness as the program that manages the conversation array. It grows a ~300-line toy agent in plain Python across 16…
   Full card: https://gitnova.dev/en/r/IsuruMaduranga/harness-engineering-101.md
5. **xerj-org/xerj** — 7.2 · Breakout · AI agents · Rust · +197 stars measured 2026-10-20, 00:22–06:36 UTC, ≈ 1,423 by evening
   A local Rust search engine that auto-indexes folders of code, docs, logs and PDFs so AI agents retrieve exact passages instead of reading whole files. Elasticsearch-compatible and cuts token usage for agents.
   Full card: https://gitnova.dev/en/r/xerj-org/xerj.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 2026-10-20 06:47 UTC, updated every 30 minutes.