| Name | Version | Summary | date |
| trustwise |
1.0.0b10 |
Trustwise Python SDK for interacting with the Trustwise APIs |
2025-10-07 21:51:08 |
| venai |
1.28.9 |
VenusAI is a secure and extensible Agent framework built for modern AI applications. |
2025-10-07 20:49:25 |
| dyff-audit |
0.13.0 |
Audit tools for the Dyff AI auditing platform. |
2025-10-07 03:19:12 |
| superagent-ai |
0.0.9 |
Python SDK for Superagent. |
2025-10-06 06:32:16 |
| dyff-schema |
0.34.1 |
Data models for the Dyff AI auditing platform. |
2025-09-19 04:07:57 |
| safety-schemas |
0.0.16 |
Schemas for Safety tools |
2025-09-16 14:35:31 |
| hertz07 |
0.1.0 |
Hertz07 Python SDK for AI safety |
2025-09-14 19:24:38 |
| judgezoo |
0.1.4 |
A collection of judges for evaluating LLM model output for safety & toxicity with a standardized API. |
2025-09-08 16:14:41 |
| dyff-client |
0.20.0 |
Python client for the Dyff AI auditing platform. |
2025-09-03 21:22:49 |
| wokcounty |
0.0.1 |
The only correct, pure, PEP 8 compliant implementation of AES-128 which do not use modes of operation, iv etc but follows the core AES-128 standard only (Details: others are either incorrect as given the same input as that specified in AES-128, it produce a different output and hence by AES-128 is deemed not compliant; or they use iv, modes of operations like CBC/ECB, padding, salt, password-based key deriviation, randomness et cetera). |
2025-09-02 12:28:57 |
| generalanalysis |
0.2.4 |
Python SDK for General Analysis Guardrails |
2025-09-01 23:37:55 |
| safety |
3.6.1 |
Scan dependencies for known vulnerabilities and licenses. |
2025-09-01 22:30:00 |
| commonpower |
0.6.1 |
A package for the exploration of safe single/multi-agent reinforcement learning in smart grids. |
2025-09-01 16:21:44 |
| ai-kill-switch |
0.0.1 |
AI Kill Switch SDK |
2025-09-01 03:58:47 |
| dyff |
0.35.1 |
Meta-package to install the local SDK for the Dyff AI auditing platform. |
2025-08-29 18:35:04 |
| wisent-guard |
0.4.46 |
Monitor and guard against harmful content in language models |
2025-08-27 23:13:21 |
| HASARD |
0.2.0 |
Egocentric 3D Safe Reinforcement Learning Benchmark |
2025-08-26 21:39:27 |
| oss-redteam |
0.1.1 |
GPT-OSS red-teaming pipeline and harness (OpenAI-compatible) |
2025-08-18 03:07:44 |
| bitfinex-api-py-postonly |
3.0.5.post2 |
Bitfinex Python API with enforced POST_ONLY orders - prevents accidental market/taker orders |
2025-08-16 11:59:05 |
| darkfield-cli |
0.2.3 |
Navigate the topology of mind - ML safety through persona vectors |
2025-08-14 16:26:27 |