AI Agents
Deep-dives on autonomous AI agent frameworks, multi-agent orchestration, and tool-use runtimes — how the systems behind agentic coding and research actually work.
292 articles
AI Agents
nono: Zero-Latency AI Agent Sandboxing Without Containers
AI Agents
Reverse Engineering the Oura Ring: How open_oura Bypasses Cloud Lock-In for Local Health Data
AI Agents
Orchestrating Multi-Agent Coding Systems in 2026: Citadel vs OMX vs OpenSpace
AI Agents
Sandboxing AI Agents in 2026: Nono vs Wardgate
AI Agents
GBrain: The AI-Native Knowledge Base That Tells You What It Doesn't Know
AI Agents
Why Your AI Coding Agent Keeps Forgetting What It Built: The Five-Subsystem Harness Solution
AI Agents
SkillOpt: Training Prompt Libraries Like Neural Networks for Frozen LLMs
AI Agents
Inside Visa's Nine-Stage LLM Pipeline for Automated Vulnerability Discovery
AI Agents
Building a Stateful Email Client on the Edge: Inside Cloudflare's Agentic Inbox
AI Agents
ALE: Evaluating AI Agents on Real Professional Work Without Giving Them the Answers
AI Agents
SCOUT-2: When Your AI Assistant Needs Admin Privileges (and Why That's a Problem)
AI Agents
SCOUT-2: When Multi-Provider LLM Abstraction Meets Desktop Reality
AI Agents
Vigolium: The Vulnerability Scanner That Runs an LLM Inside Go
AI Agents
LobeHub: The Agent Orchestration Platform That Treats AI as Your Employee, Not Your Chatbot
AI Agents
OpenSRE: Building the SWE-bench for Production Incidents
AI Agents
Agent Orchestrator: Git Worktrees Are the Secret to Parallel AI Coding
AI Agents
OpenSandbox: Building Production-Grade Isolation for AI Agents That Actually Execute Code
AI Agents
Strands Agents: The Missing Link Between MCP Servers and Multi-Provider AI Agents
AI Agents
Starlog Index: Teaching AI Agents to Stop Installing Lodash in 2025
AI Agents
aenv: Version-Controlled Environments for AI Coding Agent Configuration
AI Agents
UltraCode-Shim: Hijacking Claude Code's Premium Mode for Any LLM
AI Agents
Building Plugin Systems That Don't Suck: External Agents and the Process-Based Protocol Pattern
AI Agents
Audit: An 8-Stage LLM Pipeline That Hunts Vulnerabilities Through Adversarial Validation
AI Agents