Skip to content
@EverywhereSafety

Everywhere Safety

Safety and privacy for AI embedded in everyday life.
README.md

Everywhere Safety

As AI becomes embedded across everyday life, we study how intelligent systems can act safely, protect privacy, and remain reliable over long horizons, wherever they operate.

Explore our research at everywheresafety.github.io.

Popular repositories Loading

  1. SEAD SEAD Public

    A state-based perspective on attack and defense in tool-using agents.

    Python 4

  2. murdoku-lab murdoku-lab Public

    Generate, play and solve Murdoku-like puzzles for humans and agents. Verifiable text and visual environments.

    Python 2

  3. agent-horizon agent-horizon Public

    Long-horizon agentic RL infrastructure on veRL: persistent state, context management and asynchronous rollout

    Python 1

  4. EverywhereSafety.github.io EverywhereSafety.github.io Public

    Everywhere Safety research website

    JavaScript

  5. TurnGate TurnGate Public

    Forked from Graph-COM/TurnGate

    [ICML 2026 AIWILD] Official implementation of TurnGate, "One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue".

    Python

  6. CKA-Agent CKA-Agent Public

    Forked from Graph-COM/CKA-Agent

    [ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".

    Python

Repositories

Showing 10 of 11 repositories
  • EverywhereSafety.github.io Public

    Everywhere Safety research website

    EverywhereSafety/EverywhereSafety.github.io's past year of commit activity
    JavaScript 0 0 0 0 Updated Oct 9, 2026
  • murdoku-lab Public

    Generate, play and solve Murdoku-like puzzles for humans and agents. Verifiable text and visual environments.

    EverywhereSafety/murdoku-lab's past year of commit activity
    Python 2 AGPL-3.0 0 0 0 Updated Oct 9, 2026
  • blog Public

    Research ideas, engineering notes and project stories from Everywhere Safety

    EverywhereSafety/blog's past year of commit activity
    HTML 0 0 0 0 Updated Oct 9, 2026
  • agent-horizon Public

    Long-horizon agentic RL infrastructure on veRL: persistent state, context management and asynchronous rollout

    EverywhereSafety/agent-horizon's past year of commit activity
    Python 1 AGPL-3.0 0 0 0 Updated Oct 9, 2026
  • SEAD Public

    A state-based perspective on attack and defense in tool-using agents.

    EverywhereSafety/SEAD's past year of commit activity
    Python 4 Apache-2.0 0 0 0 Updated Sep 28, 2026
  • .github Public

    Everywhere Safety organization profile

    EverywhereSafety/.github's past year of commit activity
    0 0 0 0 Updated Sep 28, 2026
  • E-CommerceBench Public Forked from QwenLM/E-CommerceBench

    Long-horizon benchmark where 18 LLM agents got ¥100,000 each and ran simulated online stores for 365 days on real market data: negotiating with suppliers, pricing, managing inventory, keeping cash flow alive.

    EverywhereSafety/E-CommerceBench's past year of commit activity
    Python 0 Apache-2.0 16 0 0 Updated Sep 13, 2026
  • TurnGate Public Forked from Graph-COM/TurnGate

    [ICML 2026 AIWILD] Official implementation of TurnGate, "One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue".

    EverywhereSafety/TurnGate's past year of commit activity
    Python 0 AGPL-3.0 5 0 0 Updated Sep 7, 2026
  • CKA-Agent Public Forked from Graph-COM/CKA-Agent

    [ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".

    EverywhereSafety/CKA-Agent's past year of commit activity
    Python 0 AGPL-3.0 47 0 0 Updated May 20, 2026
  • ImmersedPrivacy Public Forked from immersed-privacy/immersed-privacy

    [NeurIPS 2026]

    EverywhereSafety/ImmersedPrivacy's past year of commit activity
    Python 0 GPL-3.0 1 0 0 Updated May 13, 2026
View all repositories

Top languages

Loading…

Most used topics

Loading…