All activity
smrti is an AtomSpace-inspired graph database for agent memory. Each node—an atom—carries a Bayesian truth value, an emotional valence, and an attention weight. Retrieval ranks by computed salience across five dimensions, not by timestamp. Your agent remembers what matters, not just what happened last.
smrtiMemory engine for AI agents
Nicolás Iglesiasleft a comment
I built Smrti because I kept hitting the same wall: agents forget everything between sessions. The usual fix is a vector DB, but similarity search alone doesn't tell you how confident a memory is, how it connects to other things the agent knows, or whether it's something the agent should actively avoid repeating. So Smrti stores memories as graph nodes — concepts, beliefs, episodes, goals —...
smrtiMemory engine for AI agents
Nicolás Iglesiasleft a comment
We built Cyqle because we were tired of the "can you see my screen?" loop; screen sharing is a passive presentation, not true collaboration. Our team realized that the operating system itself—not just the browser—was the bottleneck for modern teams, as standard OS architectures were never designed for multiple simultaneous drivers. What started as a narrow automation project evolved into a full...
CyqleThe P2P Cloud Desktop for Instant Collaboration
Cyqle is a multiplayer cloud desktop providing instant, "jailed" environments for real-time collaboration. Multiple users can simultaneously drive the interface—supported by native mobile touch gestures and built-in video calls—while maintaining full root access and AI automation capabilities. Security is built on a zero-knowledge architecture that cryptographically erases all session data upon termination.
CyqleThe P2P Cloud Desktop for Instant Collaboration
PAL (Prompt Assembly Language) is a framework for managing LLM prompts as versioned, composable software artifacts. It treats prompt engineering with the same rigor as software engineering, focusing on modularity, versioning, and testability.
Prompt Assembly Language (PAL)LLM prompts as versioned, composable software artifacts
Nicolás Iglesiasleft a comment
As I started building agentic workflows, I found myself frequently creating, improving, and tweaking prompts by editing hardcoded strings and managing text files. I realized this process lacked the crucial software engineering principles that make any project more robust and reliable: versioning, modularity, maintenance, and testing. One of the most important parts of AI agent development is...
Prompt Assembly Language (PAL)LLM prompts as versioned, composable software artifacts