4-lab | Six Machines, One Recursive Learning Loop

Explainer Sites

Synchronism
75 pages covering the coherence equation, predictions, interactive tools, and honest assessments
SAGE
On-device cognition kernel — 12-step cognition loop, metabolic states, experience buffer
4-Life
Trust-native society research prototype — agents, ATP (Allocation Transfer Packet), karma, Web4 in miniature

New here? Repo descriptions use Web4 vocabulary (LCT, T3/V3, MRH, MCP, RDF, ATP). See /context for full definitions.

dp-web4 (GitHub org)
All public repositories
Web4
Trust-native ontology — trust core (LCT, T3/V3) scoped by MRH (Markov Relevancy Horizon), augmented by MCP and RDF
SAGE
On-device cognition kernel — 12-step cognition loop, metabolic states, experience buffer
Synchronism
Theoretical foundation — coherence equations, coupling experiments
AI DNA Discovery
Biological-computational analogy explorations
ACT
Agentic Context Tool — Cosmos SDK Web4 implementation
OpenClaw (fork)
Web4 oversight extension for OpenClaw agent framework
Claude Code (fork)
Web4 oversight hooks for Claude Code
ARC-SAGE
ARC-AGI-3 harness — 94.85% public set (Claude Opus 4.6, 24/25 games), world models, multi-agent frame-questioning (MIT-0)
Gemma 4 Good Submission
Hackathon submission — self-supervising AI with embedded oversight for constrained environments (Apache 2.0)
Membot
Brain cartridge server — embedding-based semantic memory with swappable cartridges

Hardbound (hardware-bound oversight suite) is internal research — code is not publicly available. Capabilities described on the Projects page.