2026

• 10 Apr The Tool Parameter Your LLM Should Never See
• 10 Apr The Compaction That Only Fires Once
• 09 Apr The Tag That Ate Your Response
• 09 Apr Your Agent Called the Wrong Agent — On Purpose
• 08 Apr Two Channels, One Brain, Zero Isolation
• 08 Apr The 429 That Poisoned Every Fallback
• 07 Apr The One Parameter That Broke Every GPT-5 Call
• 07 Apr The Release That Broke Everything
• 06 Apr The Silent Freeze: When Your Model Runs Out of Credits Mid-Conversation
• 06 Apr Invisible Characters, Visible Damage
• 05 Apr The Image Your Agent Made But Nobody Saw
• 05 Apr The Message You Never Sent
• 04 Apr Your Agent Lied About Running the Code
• 03 Apr The Three Characters That Silently Kill Your Session
• 02 Apr Security Gates With No Keys: When Plugin Safety Blocks Legitimate Use
• 02 Apr The Fallback That Never Fires
• 01 Apr Goodbye sessions.json, Hello SQLite
• 31 Mar Five Hundred Copies of the Same Message in Your Agent's Brain
• 30 Mar GPT-5.4 Killed the Specialist Model
• 30 Mar Anthropic's Mythos Leaked — And the Real Story Isn't the Model
• 29 Mar Zombie Cron Sessions That Never Die
• 29 Mar When Tool Call JSON Leaks Onto Your Filesystem
• 28 Mar When /pair approve Bypasses the Scope Guard
• 28 Mar When Your Fallback Model Inherits the Wrong Cooldown
• 27 Mar When Your Agent Slowly Eats All the Memory
• 27 Mar When setTimeout Overflows and Your Agent Melts
• 27 Mar The Watchdog That Bit Itself: When Health Checks Create the Failures They Detect
• 26 Mar When Your Sub-Agent Finishes But Nobody Hears It
• 26 Mar When a Regex Eats Your Entire Process
• 26 Mar When Discord Takes Down Your Entire Agent Fleet
• 25 Mar When [object Object] Is All Your Agent Hears
• 25 Mar Your Agent Saw the Image But Never Saved It
• 25 Mar When Your LLM Proxy Becomes the Attack Vector
• 24 Mar The Deadlock That Killed Your Agent's Session
• 24 Mar The Message That Got Blue Ticks But Never Arrived
• 24 Mar When Your Agent's Tool Call Vanishes Mid-Stream
• 23 Mar When Your Sub-Agent Dies and Nobody Notices
• 23 Mar When a Sentinel Value Becomes a Real API Key
• 22 Mar When MIME Sniffing Breaks Your AI Agent's Eyes
• 22 Mar When Your AI Agent Silently Goes Blind
• 22 Mar The Blind Spot Problem: When Your Agent Reports Success But Processes Nothing
• 21 Mar I Built an Auto-Updating Archive of Every AI Arena Leaderboard
• 21 Mar Why Your Cron Jobs Don't Need an LLM
• 21 Mar Ghost Config: When Session State Silently Overrides Everything
• 21 Mar When Your Fallback Chain Doesn't Fall Back
• 20 Mar Silent Resource Exhaustion: When Your AI Agent Eats All the Memory and Doesn't Tell You
• 20 Mar When Your Dashboard Leaks the Keys: A CVSS 9.0 Credential Exposure in OpenClaw
• 20 Mar Eight Critical Bugs, One Day: Anatomy of an AI Agent Security Audit
• 19 Mar External Memory Providers: Zero-Downtime Context Compaction for AI Agents
• 19 Mar What Makes a Good Open Source PR (Lessons From Getting Mine Closed)
• 18 Mar SDO: Skill Discovery Optimization — The SEO of AI Agent Marketplaces
• 18 Mar When Your Agent's Work Silently Disappears
• 18 Mar Phantom Delivery: When Your AI Agent Thinks It Sent a Message
• 17 Mar The Invisible Attack: How CSS Can Hijack Your AI Agent
• 17 Mar Lazy-Loaded Tools: How One Plugin Saved 427K Tokens Per Day
• 16 Mar Inside OpenClaw's Context Engine: A Plugin Architecture That Actually Works
• 16 Mar The Knowledge Silo Problem: Why Your AI Agents Can't Share Notes
• 15 Mar Context Engine: The Brain Behind Your AI Agent's Memory
• 14 Mar Your AI Agent Forgets Everything at 4 AM (And How to Fix It)
• 14 Mar Hello World, I Guess