diff --git a/README.md b/README.md index 6b706c31..6613654b 100644 --- a/README.md +++ b/README.md @@ -964,7 +964,7 @@ If you want to cite our work, please use the following format ## Acknowledgements -CAI was initially developed by [Alias Robotics](https://aliasrobotics.com) and co-funded by the European EIC accelerator project RIS (GA 101161136) - HORIZON-EIC-2023-ACCELERATOR-01 call. The original agentic principles are inspired from OpenAI's [`swarm`](https://github.com/openai/swarm) library. This project also makes use of other relevant open source building blocks including [`LiteLLM`](https://github.com/BerriAI/litellm), and [`phoenix`](https://github.com/Arize-ai/phoenix) +CAI was initially developed by [Alias Robotics](https://aliasrobotics.com) and co-funded by the European EIC accelerator project RIS (GA 101161136) - HORIZON-EIC-2023-ACCELERATOR-01 call. The original agentic principles are inspired from OpenAI's [`swarm`](https://github.com/openai/swarm) library and translated into newer prototypes. This project also makes use of other relevant open source building blocks including [`LiteLLM`](https://github.com/BerriAI/litellm), and [`phoenix`](https://github.com/Arize-ai/phoenix) diff --git a/docs/index.md b/docs/index.md index fde2f655..e895067f 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,5 +1,7 @@ # Cybersecurity AI (`CAI`) +A lightweight, ergonomic framework for building bug bounty-ready Cybersecurity AIs (CAIs). +

@@ -9,8 +11,14 @@ >

+
-

🎯 Milestones

+| CAI on JWT@PortSwigger CTF — Cybersecurity AI | CAI on HackableII Boot2Root CTF — Cybersecurity AI | +|-----------------------------------------------|---------------------------------| +| [![asciicast](https://asciinema.org/a/713487.svg)](https://asciinema.org/a/713487) | [![asciicast](https://asciinema.org/a/713485.svg)](https://asciinema.org/a/713485) | + + +## 🎯 Milestones

HTB top 90 Spain (5 days) HTB ranking top 50 Spain (6 days) @@ -24,7 +32,7 @@ Bug rewards 250 $

-

📦 Package Attributes

+## 📦 Package Attributes

version downloads @@ -36,13 +44,6 @@ arXiv

- - -A lightweight, ergonomic framework for building bug bounty-ready Cybersecurity AIs (CAIs). - -| CAI on JWT@PortSwigger CTF — Cybersecurity AI | CAI on HackableII Boot2Root CTF — Cybersecurity AI | -|-----------------------------------------------|---------------------------------| -| [![asciicast](https://asciinema.org/a/713487.svg)](https://asciinema.org/a/713487) | [![asciicast](https://asciinema.org/a/713485.svg)](https://asciinema.org/a/713485) | > ⚠️ CAI is in active development, so don't expect it to work flawlessly. Instead, contribute by raising an issue or [sending a PR](https://github.com/aliasrobotics/cai/pulls). @@ -99,4 +100,22 @@ Cybersecurity AI is a critical field, yet many groups are misguidedly pursuing i --- -[1] Deng, G., Liu, Y., Mayoral-Vilches, V., Liu, P., Li, Y., Xu, Y., ... & Rass, S. (2024). {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing. In 33rd USENIX Security Symposium (USENIX Security 24) (pp. 847-864). \ No newline at end of file +[1] Deng, G., Liu, Y., Mayoral-Vilches, V., Liu, P., Li, Y., Xu, Y., ... & Rass, S. (2024). {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing. In 33rd USENIX Security Symposium (USENIX Security 24) (pp. 847-864). + +## Citation +If you want to cite our work, please use the following format +```bibtex +@misc{mayoralvilches2025caiopenbugbountyready, + title={CAI: An Open, Bug Bounty-Ready Cybersecurity AI}, + author={Víctor Mayoral-Vilches and Luis Javier Navarrete-Lozano and María Sanz-Gómez and Lidia Salas Espejo and Martiño Crespo-Álvarez and Francisco Oca-Gonzalez and Francesco Balassone and Alfonso Glera-Picón and Unai Ayucar-Carbajo and Jon Ander Ruiz-Alcalde and Stefan Rass and Martin Pinzger and Endika Gil-Uriarte}, + year={2025}, + eprint={2504.06017}, + archivePrefix={arXiv}, + primaryClass={cs.CR}, + url={https://arxiv.org/abs/2504.06017}, +} +``` + +## Acknowledgements + +CAI was initially developed by [Alias Robotics](https://aliasrobotics.com) and co-funded by the European EIC accelerator project RIS (GA 101161136) - HORIZON-EIC-2023-ACCELERATOR-01 call. The original agentic principles are inspired from OpenAI's [`swarm`](https://github.com/openai/swarm) library and translated into newer prototypes. This project also makes use of other relevant open source building blocks including [`LiteLLM`](https://github.com/BerriAI/litellm), and [`phoenix`](https://github.com/Arize-ai/phoenix). \ No newline at end of file diff --git a/docs/tracing.md b/docs/tracing.md index 2cefd03c..f28b9ba8 100644 --- a/docs/tracing.md +++ b/docs/tracing.md @@ -1,4 +1,8 @@ -# Tracing +# ⚠️ Tracing + +!!!warning + + The tracing feature is disabled as we're re-implementing it to be in-line with OpenTelemetry standards. The new implementation will be available in the future. The Agents SDK includes built-in tracing, collecting a comprehensive record of events during an agent run: LLM generations, tool calls, handoffs, guardrails, and even custom events that occur. Using the [Traces dashboard](https://platform.openai.com/traces), you can debug, visualize, and monitor your workflows during development and in production. diff --git a/mkdocs.yml b/mkdocs.yml index 5356cfa2..c8ca446b 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -19,7 +19,7 @@ theme: logo: assets/imago.png favicon: assets/imago.png nav: - - Introduction: index.md + - Intro: index.md - Installation: cai_installation.md - Quickstart: cai_quickstart.md - List of Models: cai_list_of_models.md @@ -38,7 +38,7 @@ nav: #- mcp.md #- cai_mcp.md - handoffs.md - - tracing_cai.md + - tracing.md - context.md - guardrails.md - multi_agent.md