Who should use agent-safety-bench-envs?

agent-safety-bench-envs is an open-source project built for AI safety researchers and developers.

What platforms does agent-safety-bench-envs run on?

agent-safety-bench-envs runs on the command line. It can also be self-hosted.

Is agent-safety-bench-envs still active?

Unverified. agent-safety-bench-envs has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.

What projects are similar to agent-safety-bench-envs?

Similar projects tracked by PulseGate include agentbench-cli, benchskills, and proofbench.

Back to the index

agent-safety-bench-envs

PyPIInfrastructure

agent-safety-bench-envs is an open-source package providing tool environments for the Agent Safety Bench (ASB) benchmark. It enables researchers and developers to evaluate and test the safety of AI agents using customizable scenarios and CLI tools.

Open SourceApache-2.0CLISelf-hosted

Visit PyPI

Overview

5 features

In the LLM eval & observability space, agent-safety-bench-envs takes a focused approach. It focuses on enabling researchers to benchmark and evaluate the safety of AI agents in controlled environments. It is built as an open-source project for AI safety researchers and developers. agent-safety-bench-envs is open source under the Apache-2.0 license. agent-safety-bench-envs is available on the command line, and it can be self-hosted.

agent-safety-bench-envs first shipped in 2026. Key capabilities include benchmark environments, agent safety testing, and CLI interface.

Summary written by a language model from the project’s public pages.

Benchmark environments
Agent safety testing
CLI interface
Custom scenarios
Open source

Built with & integrations

Runs on

CLISelf-hosted

Trust & compliance

License

Apache-2.0

Verified signals

HTTPSOpen SourceFree tier

Indexing history

What PulseGate has recorded for this listing

Indexed27 Jun · 08:09 UTC
Listing verified against its public source
Source: PulseGate · Open

Frequently asked questions about agent-safety-bench-envs

What is agent-safety-bench-envs?: Agent-safety-bench-envs focuses on enabling researchers to benchmark and evaluate the safety of AI agents in controlled environments. It is catalogued under LLM eval & observability on PulseGate.
Who should use agent-safety-bench-envs?: agent-safety-bench-envs is an open-source project built for AI safety researchers and developers.
Does agent-safety-bench-envs have a free plan?: Yes — agent-safety-bench-envs is open source under the Apache-2.0 license and free to use.
What platforms does agent-safety-bench-envs run on?: agent-safety-bench-envs runs on the command line. It can also be self-hosted.
Is agent-safety-bench-envs still active?: Unverified. agent-safety-bench-envs has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
What projects are similar to agent-safety-bench-envs?: Similar projects tracked by PulseGate include agentbench-cli, benchskills, and proofbench.agentbench-cli benchskills proofbench
When did agent-safety-bench-envs launch?: agent-safety-bench-envs first shipped in 2026.
Is agent-safety-bench-envs open source?: Yes — agent-safety-bench-envs is open source under the Apache-2.0 license.

At a glance

Platforms: Cli
Languages: English
License: Apache-2.0
Built for: AI safety researchers and developers
Model: Open source
Solves: Enabling researchers to benchmark and evaluate the safety of AI agents in controlled environments.

Registered as

PyPI: agent-safety-bench-envs

Developer

Pypi

Index record

Identity confidence: Low · 64
Indexed: 27 Jun 2026
Lifecycle: Alive
Last seen: 27 Jun 2026

Identity audit (12)

Slug: agent-safety-bench-envs-pypi-org
Lifecycle last checked: 8 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 27 Jun 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Canonical URL: https://pypi.org/project/agent-safety-bench-envs

Ship this? Send a correction — no account, and you get a link to follow it.

Similar projects

Closest matches by what these projects do