#security research
1903 related articles
Product Reviews·2 min
AgentSys Open-Source Framework: 49 Agents Automating Everything Beyond AI Coding
AgentSys is an open-source AI Agent automation framework with 20 plugins, 49 Agents, and 41 skills that integrates with Claude Code, Cursor, and other AI coding tools to automate project management, testing, deployment, and more.
Read more →
Research·3 min
UK AISI Evaluates GPT-5.5 Cybersecurity Capabilities: On Par with Claude Mythos but Already Publicly Available
UK AI Safety Institute (AISI) evaluates GPT-5.5 cybersecurity capabilities, finding vulnerability discovery on par with Claude Mythos. The key difference: GPT-5.5 is already publicly available, raising urgent AI safety governance concerns.
Read more →
Tutorials·2 min
Unsloth Tutorial: A Guide to Fine-Tuning LLMs Locally with Reduced VRAM and Faster Training
Learn how Unsloth enables efficient local LLM fine-tuning with LoRA optimization, supporting Gemma 4, Qwen3, and DeepSeek while reducing VRAM usage by 50% and boosting training speed 2-5x.
Read more →
Product Reviews·3 min
Deep Dive into CowAgent: The Open-Source AI Assistant with 44,000 Stars
Deep dive into CowAgent (formerly chatgpt-on-wechat), a 44K-star GitHub project offering Agent capabilities, multi-platform integration with WeChat/Feishu, and multi-model support including DeepSeek.
Read more →
Product Reviews·1 min
Unsloth: An Efficient Open-Source Tool for Local LLM Fine-Tuning
Unsloth is a 63,000+ star open-source project on GitHub with a Web UI for locally training and fine-tuning LLMs like Gemma 4, Qwen3, and DeepSeek on consumer GPUs.
Read more →
Product Reviews·3 min
Refly Open-Source Agent Skills Builder: A New Paradigm for Cross-Platform AI Skill Development
Deep dive into Refly, an open-source Agent Skills Builder featuring Vibe Workflow visual skill definition, cross-platform execution on Claude Code/Cursor, and a new "skills as infrastructure" paradigm for AI Agent development.
Read more →
Tutorials·3 min
Ollama Tutorial: The Complete Guide to Running Large Models Locally (2025 Updated)
Complete guide to deploying LLMs locally with Ollama. Supports DeepSeek, Qwen, Kimi-K2.5 and more. 170K GitHub Stars, one-click install, full data privacy, zero API costs.
Read more →
Research·3 min
UK AISI Assessment Report: GPT-5.5 Cybersecurity Capabilities on Par with Claude Mythos
UK AISI releases GPT-5.5 cybersecurity assessment showing vulnerability discovery capabilities on par with Claude Mythos, but with GPT-5.5 already publicly available, raising new AI safety governance concerns.
Read more →
Deep Dives·2 min
Open Multi-Agent: A TypeScript Multi-Agent Orchestration Framework with Automatic Task DAG Generation
Deep dive into Open Multi-Agent, a TypeScript-native multi-agent orchestration framework with automatic task DAG generation, MCP integration, live tracing, and only three runtime dependencies. 6000+ GitHub Stars.
Read more →
Deep Dives·3 min
754 Cybersecurity Skills Library: An Analysis of the Open-Source AI Agent Security Capability Map
Anthropic open-sources 754 structured cybersecurity skill definitions across 26 domains, mapped to MITRE ATT&CK and 4 other frameworks, compatible with 20+ AI platforms for standardized AI Agent security capabilities.
Read more →
Tech Frontiers·3 min
Strands Agents: An Open-Source SDK for Building AI Agents in Just a Few Lines of Python
Strands Agents is a trending GitHub project using model-driven design to let developers build AI Agents in just a few lines of Python. Learn its philosophy, use cases, and advantages over LangChain.
Read more →
Research·2 min
UK AI Safety Institute Evaluates GPT-5.5: Cybersecurity Capabilities on Par with Claude Mythos
UK AISI evaluates GPT-5.5 cybersecurity capabilities, finding vulnerability discovery on par with Claude Mythos — but GPT-5.5 is already publicly available, raising new security concerns.
Read more →
Tech Frontiers·1 min
UK AI Safety Institute Evaluates GPT-5.5's Cybersecurity Capabilities
The UK AI Safety Institute finds GPT-5.5's cybersecurity vulnerability discovery capabilities on par with Claude Mythos, but GPT-5.5 is already publicly available.
Read more →
Product Reviews·1 min
Ollama: The Ultimate Tool for Running Large Models Locally
Ollama is an open-source tool with 170K+ GitHub stars that lets you run LLMs like DeepSeek, Qwen, and Gemma locally with just a few commands.
Read more →
Product Reviews·1 min
gpt4free: An Analysis of the Open-Source Project for Free Access to Top-Tier LLMs
An in-depth analysis of gpt4free, the 66K-star open-source project offering free access to GPT-5.3, Claude, Gemini and more top AI models.
Read more →
Product Reviews·1 min
ClawCode: A Multi-Model Coding Agent CLI Built with Python + Rust
ClawCode is an open-source coding agent CLI built with Python and Rust, supporting 200+ AI models with experience-based evolution capabilities.
Read more →
Product Reviews·1 min
Unsloth: A Powerful Tool for Locally Training and Running Open-Source LLMs
Unsloth is an open-source tool with 63K+ GitHub stars for locally training and running LLMs like Gemma 4, Qwen3.6, and DeepSeek with optimized VRAM usage.
Read more →
Tech Frontiers·1 min
Open-Source Replication of Anthropic Mythos: Autonomous Vulnerability Discovery Framework Analysis
Analysis of mythos-research, an open-source replication of Anthropic's Mythos Preview autonomous vulnerability discovery framework using Claude Opus 4.7.
Read more →
Product Reviews·4 min
RuoYi-AI Open Source Framework: A One-Stop Solution for Java Enterprise AI Application Development
A deep dive into RuoYi-AI, a Java-based enterprise AI development platform supporting multi-vendor LLM integration, RAG knowledge bases, and agent orchestration. 5,200+ Stars on GitHub.
Read more →
Product Reviews·2 min
OpenYak: Open-Source Local AI Agent Supporting 100+ Models with Zero Telemetry Privacy
OpenYak is an open-source local AI agent supporting Windows/macOS/Linux. Access 100+ models via OpenRouter, MCP, and Ollama with BYOK zero-telemetry privacy — a strong alternative to Claude Code and OpenAI Codex.
Read more →