The research library / Six connected fields
Good questions
deserve a closer look.
Working questions, experiments, and methods behind the software. Browse by field or follow a topic into its context and related work.
17 of 47 research topics · AI systems
ALX Semantic Compiler
AI systemsSource-preserving semantic compilation, execution contracts, and bounded repair with explicit evaluation limits.
ActiveProtocol Compiler Framework
AI systemsA repeatable method for compiling research and operating rules into agent-usable protocols.
CanonicalALX LoRA Evaluation Track
AI systemsEvaluation plans for whether specialized training can preserve ALX structure and reversibility.
CurrentHome Base Agent OS
AI systemsProject registry, memory, governance, source ledgers, and recovery paths for long-running agent work.
ActiveTask-Aware Context Rollover & Recovery v1.1
AI systemsA protocol for preserving intent, evidence, and next actions when context windows or sessions change.
CanonicalAI Fundamentals & Markdown Transformer Compiler
AI systemsA structured language and transformation lane for turning raw knowledge into agent-readable artifacts.
CurrentForge Scheduler / FOS
AI systemsResearch into scheduling, bounded execution, and operating-system-like coordination for agent workflows.
PrototypeBrowser Agent Consultation Prompt Pack
AI systemsReusable consultation patterns for browser agents that separate observation, judgment, and action.
CurrentCompute Broker-Dealer
AI systemsA prompt and architecture track for allocating compute, models, and work according to task value and constraints.
PrototypeMCP-First UI & Agent Pipelines
AI systemsInterface patterns where tools, permissions, evidence, and agent actions remain explicit from protocol to UI.
ActiveFramework Selection Protocol Forge
AI systemsEvidence-led framework selection, including a current Svelte agentic-coding research branch.
SeriesShared Skills Library
AI systemsPortable skills and operating instructions designed to transfer across tools and model providers.
ActiveNeuron Protocols
AI systemsProvider-independent orchestration, scoped retrieval, tools, memory, and surface-aware interaction.
ActiveLaya and Jev Decision Probe
AI systemsA small typed-decision comparison and a test of prompt routing for arithmetic, with the limits kept visible.
PrototypePersistent Agent Memory
AI systemsPortable project notes and explicit recovery state across assistants and sessions.
ActiveDeterministic Prompt Routing
AI systemsRoute tasks to operating protocols without making provider identity part of the decision.
ActiveScope & Execution Contracts
AI systemsDefine observable acceptance criteria, constraints, and named authority before a broad build.
CanonicalThis library presents public summaries of research programs and methods. A topic’s presence here does not imply a published paper or a validated result; individual briefs distinguish the available summary from the work still under investigation.