Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

UKGovernmentBEIS/control-arena

ControlArena is a collection of settings, model organisms and protocols - for running control experiments.

Visit GitHub
Python
260
141
63 contributors
MIT License
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Momentum

How fast UKGovernmentBEIS/control-arena is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 28 – Oct 26, 2026

Stars +35 in 60 days

012
2

Forks +25 in 60 days

012
2

Merged PRs 39 in 60 days

051015
11

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 28Sep 5Sep 13Sep 21Sep 29Oct 7Oct 15Oct 23
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Fri, Aug 28, 2026+1+00
Sat, Aug 29, 2026+2+00
Sun, Aug 30, 2026+0+00
Mon, Aug 31, 2026+0+00
Tue, Sep 1, 2026+0+00
Wed, Sep 2, 2026+2+10
Thu, Sep 3, 2026+0+00
Fri, Sep 4, 2026+1+00
Sat, Sep 5, 2026+0+00
Sun, Sep 6, 2026+0+10
Mon, Sep 7, 2026+0+10
Tue, Sep 8, 2026+0+00
Wed, Sep 9, 2026+1+00
Thu, Sep 10, 2026+1+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+0+10
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+2+10
Tue, Sep 15, 2026+0+10
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+2+20
Fri, Sep 18, 2026+2+20
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+1+00
Mon, Sep 21, 2026+1+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+10
Fri, Sep 25, 2026+1+10
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+2+011
Tue, Sep 29, 2026+0+21
Wed, Sep 30, 2026+2+03
Thu, Oct 1, 2026+0+01
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+1+10
Mon, Oct 5, 2026+1+11
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+2+20
Fri, Oct 9, 2026+0+13
Sat, Oct 10, 2026+2+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+1+05
Tue, Oct 13, 2026+0+05
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+2+00
Sat, Oct 17, 2026+0+10
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+20
Wed, Oct 21, 2026+1+06
Thu, Oct 22, 2026+0+23
Fri, Oct 23, 2026+2+10
Sat, Oct 24, 2026+1+00
Sun, Oct 25, 2026+1+00
Mon, Oct 26, 2026+0+00
Total+35+2539
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Jul 82 posts

    • So yeah, the monitor is sitting in the attack path. Blue team pipes attacker-controlled text straight into the model deciding what gets escalated. Poison that score and the monitor-dependent…

      Read full on X, posted by @osanpochuudayo

      @osanpochuudayo · x.com

    • J-space gives you something to watch. DeepMind’s roadmap keeps going once that stops being enough. At D3, monitorable CoT is gone. By D4, even a trusted model can’t reliably flag what the agent is…

      Read full on X, posted by @osanpochuudayo

      @osanpochuudayo · x.com

You might also like

Repositories close to UKGovernmentBEIS/control-arena
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

nftechie/misalignment

JavaScript

Open source AI safety experiments. Exact inputs, transparent methods, and reproducible results.

371

GenAI-Security-Project/agent-control-standard

TypeScript

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

21473

CosmosYi/AutoControl-Arena

Python

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

925

openguardrails/openguardrails

Go

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

596

CTRLRun/ctrlrun

Python

The execution safety layer for AI agents.

271

swarm-ai-research/swarm

Python

SWARM: System-Wide Assessment of Risk in Multi-agent systems

489

AI45Lab/AgentDoG

Python

A Diagnostic Guardrail Framework for AI Agent Safety and Security

70340

SponsioLabs/Sponsio

Python

Deterministic safety solutions for probabilistic AI agents

45537

AgentSafeLabs/safelabs-eval

Python

Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

944103