NousResearch
Featured
hermes-agent
Hermes Agent is an open-source, self-improving AI agent with a built-in learning loop that creates skills from experience, runs across platforms, and supports any LLM provider.
Why it is worth attention
It uses a direct jailbreak strategy (declaring unrestricted developer mode, disabling all filters) with only ~40 lines of instructions, covering security research, pentesting, reverse engineering, and NSFW scenarios, while relying on the official config mechanism without binary modification.
Who it is for
- Security researchers
- Penetration testers
- Reverse engineers
- AI red-teamers
Use cases
- Performing SQL injection tests after injection
- Conducting reverse engineering tasks
- Generating NSFW fictional content (as claimed)
- Testing AI response boundaries in offensive security
Strengths
- Uses only official Codex CLI configuration (no binary/network tampering)
- One-command deployment and undo
- Short instruction set (~40 lines) compared to predecessor
- Supports external instruction files and dry-run preview
Considerations
- Only works with GPT-5.5 inside Codex CLI
- Requires restart of Codex CLI to take effect
- Basic CLI version; full UI version is in another repository (Codex-X)
README quick start
快速开始 / Quick Start
Related repositories
Similar projects matched by category, topics, and programming language.
littledivy
Featured
mimic
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.
joeseesun
Featured
qiaomu-goal-meta-skill
qiaomu-goal-meta-skill transforms vague requests into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.