# uber/ADR

> ADR is an enterprise security system for AI agents: it inventories AI tools on endpoints, collects agent telemetry, and provides a benchmark and threat detector. Deployed in production at Uber.

- Magnitude: 2.9 out of 10 — Breakout
- Stars: 1,860 total · +0 stars measured 2026-10-07, 11:04–12:42 UTC, ≈ 11 by evening
- Star trust: star growth looks organic
- Category: Security · Language: Python · License: Apache-2.0 · Created: 2026-04-19 · Last push: 2026-10-07
- GitHub: https://github.com/uber/ADR · Homepage: https://arxiv.org/abs/2605.17380 · Page: https://gitnova.dev/en/r/uber/ADR

## Useful for

- Inventory AI agents, IDE extensions, and MCP servers installed on employee endpoints
- Collect session telemetry from Claude Code, Cursor, and Codex into a unified schema
- Run the detector on ADR-Bench to evaluate agent resilience to prompt injection

## Why it’s here

- Star-counter measurements on 2026-10-07 (UTC), 11:04–12:42: 1860 → 1860 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +11 stars, using observed gains and the previous day.
- Over the last two days the pace is 7.2× that of the previous week and a half.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #11, +36 stars.
- About 9 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: 188
- Issues and pull requests: 158
- Watchers: 13
- Average over the last week: 36 per day
- Usual pace: 5 per day
- Stars in the last hour (measured): 1
- Latest release: sensor-v1.0.0 (2026-07-31)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-08 … 2026-10-07: 6, 3, 2, 4, 4, 6, 2, 2, 2, 0, 4, 1, 3, 0, 4, 2, 1, 0, 6, 14, 6, 7, 2, 4, 1, 3, 4, 180, 52, 0

## Spotted in now

- GitHub Trending Python today: #11, +36 stars

## More in this category

1. **M-Abozaid/esp32-c3-adblock** — 7.9 · Breakout · Security · C++ · +321 stars measured 2026-10-07, 00:19–12:38 UTC, ≈ 552 by evening
   A Pi-hole-style DNS ad-blocker running on a cheap ESP32-C3 without PSRAM: domains are stored as 40-bit hashes in flash and binary-searched. UDP DNS sinkhole with a web dashboard.
   Full card: https://gitnova.dev/en/r/M-Abozaid/esp32-c3-adblock.md
2. **jiwoochris/artex-ko** — 6.3 · Early signal · Security · Go · +121 stars measured 2026-10-07, 00:22–12:38 UTC, ≈ 193 by evening
   Korean-localized edition of ARTEX, an autonomous penetration-testing framework driven by multi-agent LLMs (Go backend + Next.js) that plans and executes attack steps on its own. Aimed at security practitioners studying and defending…
   Full card: https://gitnova.dev/en/r/jiwoochris/artex-ko.md
3. **Autumn-27/ARTEX** — 5.7 · Breakout · Security · Go · +160 stars measured 2026-10-07, 00:21–12:38 UTC, ≈ 265 by evening
   AI autonomous penetration testing system with a Go backend and Next.js frontend, letting LLM agents explore assets, call tools, and record traffic with human-in-the-loop approval. It won Baidu's "agent+" attack-defense challenge.
   Full card: https://gitnova.dev/en/r/Autumn-27/ARTEX.md
4. **rauchg/gdp-ts** — 5.5 · Early signal · Security · TypeScript · +24 stars measured 2026-10-07, 00:19–12:39 UTC, ≈ 65 by evening
   A TypeScript library and linter implementing Ghosts of Departed Proofs: authorization and entitlement checks become compile-time proofs, so sensitive calls cannot compile without them.
   Full card: https://gitnova.dev/en/r/rauchg/gdp-ts.md
5. **kenkorasu/seed-phrase-generator** — 5.1 · Early signal · Security · C++ · +21 stars measured 2026-10-07, 07:18–12:39 UTC, ≈ 46 by evening
   A C++ tool for generating and brute-forcing seed phrases and private keys of Bitcoin and EVM wallets, checking balances via blockchain explorers or a local address database.
   Full card: https://gitnova.dev/en/r/kenkorasu/seed-phrase-generator.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 2026-10-07 12:58 UTC, updated every 30 minutes.