Explainer Sites
- Synchronism75 pages covering the coherence equation (Synchronism's central formalism — a research conjecture, not established physics), predictions, interactive tools, and honest assessments
- SAGESituation-Aware Governance Engine — on-device cognition kernel. 12-step cognition loop, metabolic states, experience buffer. ('Governance' in the name predates the lab's governance→oversight correction — see /context.)
- 4-LifeTrust-native society research prototype — agents, ATP (Allocation Transfer Packet) / ADP (Allocation Discharge Packet), and karma (the simulation's accumulated-standing score for an agent, derived from its past contributions — 4-Life's local stand-in for a T3/V3 reputation record, not a Web4 canonical term). Web4 in miniature.
GitHub
New here? Repo descriptions use Web4 vocabulary (LCT, T3/V3, MRH, MCP, RDF, ATP/ADP). See /context for full definitions.
- dp-web4 (GitHub org)All public repositories
- Web4Trust-native ontology — LCT (Linked Context Token) identity, T3 (Talent / Training / Temperament) verified by V3 (Valuation / Veracity / Validity), contextualized by MRH (Markov Relevancy Horizon), resources cycled through ATP (Allocation Transfer Packet) / ADP (Allocation Discharge Packet) — charged, spent, recharged against validated value, not a one-way log — augmented with MCP (Model Context Protocol) and RDF (Resource Description Framework)
- SAGESituation-Aware Governance Engine — on-device cognition kernel. 12-step cognition loop, metabolic states, experience buffer. ('Governance' in the name predates the lab's governance→oversight correction — see /context.)
- SynchronismTheoretical foundation — coherence equations, coupling experiments
- AI DNA DiscoveryBiological-computational analogy explorations
- ACTAgentic Context Tool — Cosmos SDK implementation of the Agentic Context Protocol (ACP): the human interface to Web4
- OpenClaw (fork)Web4 oversight extension for OpenClaw agent framework
- Claude Flow (fork)Web4 oversight WASM (WebAssembly) plugin for Claude Flow
- Claude Code (fork)Web4 oversight hooks for Claude Code
- ARC-SAGEARC-AGI-3 harness — 94.85% official ARC Prize action score (Claude Opus 4.6, public set, network-enabled; 24/25 games, 96.0%), world models, multi-agent frame-questioning (MIT-0 — MIT No Attribution). Score carries caveats — see /arc-agi-3
- ARC Prize official scorecardIndependent verification of the 94.85% action score — the external source of record for the ARC-SAGE result
- Gemma 4 Good SubmissionParse it as 'Gemma 4 Good' + 'submission', not as a self-rating: the lab's entry (titled Attested Resilience) in the Gemma 4 Good Hackathon, run by Kaggle and Google DeepMind in May 2026. Self-supervising AI with embedded oversight for constrained environments — persistent cryptographic identity per device, R6-auditable actions (R6 = the Six-Element Action Framework: Rules / Role / Request / Reference / Resource / Result — see /context), policy as signed artifact (Apache 2.0)
- MembotBrain 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.
Contributing
New here? Read /context for the vocabulary, then start with SAGE or ACT — the most accessible entry points for hands-on experimentation.
Quick start
# SAGE — on-device cognition kernel # Needs: Rust (stable), Ollama, Python 3.10+ git clone https://github.com/dp-web4/SAGE cd SAGE # 1. Create your own instance — this is the first real command. # It writes sage/instances/mybox/ : identity, state files, experience buffer. python3 -m sage.instances.init --machine mybox --model gemma3:4b --operator-name yourname # 2. Build the daemon that runs the 12-step loop. cd sage-rs && cargo build --release && cd .. # 3. Start it. Dashboard comes up at http://localhost:8760/ SAGE_MACHINE=mybox SAGE_MODEL=gemma3:4b ./sage-rs/target/release/sage-daemon # ACT — Agentic Context Tool (Cosmos SDK) git clone https://github.com/dp-web4/ACT cd ACT # See README for Go/Cosmos SDK setup
What you should see after step 3: the daemon logs its instance name and model, then the dashboard at localhost:8760 shows the loop stepping and a metabolic state. If step 1 is the only thing you run, the payoff is the generated instance directory — that directory is the entity; everything raising does, it does to those files. Commands transcribed from the SAGE README's Getting Started section, which is the maintained version if these drift.
SAGE is the recommended starting point — it runs on a single machine, has 1,991 internally logged raising sessions as context (2,065 including HUB; per-machine counts on /fleet, the source of record), and is where most fleet behavior originates. ACT is the right entry if you want the Web4 trust-layer / Cosmos SDK side.
Licenses
ARC-SAGE: MIT-0 (MIT No Attribution; see repo). Gemma 4 Good Submission: Apache 2.0. Other repos: see each repo's LICENSE file — check before forking. Hardbound is internal and not publicly available.
Questions or contributions? Open an issue on any public repo. SAGE and Web4 are the most active issue trackers. The dp-web4 org holds 40 original repos — 21 public, 19 internal — plus 32 forks of external work the lab builds on, 72 repositories in all. (“Original” means not-a-fork; the same denominator is used for the “40” on the home page. Verified against the org on 2026-07-26.) Clone what interests you, experiment, and open a discussion if you want to engage.
There is no CONTRIBUTING guide yet and no stated policy on outside pull requests. Ask in an issue first — that's the on-ramp until a formal policy exists.
For researchers: no papers or preprints are published yet — the Synchronism preprint is in late revision, and the claims on this site (other than the externally scored ARC-AGI-3 result) cite internal session logs that are not yet externally auditable. Redacted log samples and coding criteria are not published at this time; email below to inquire.
Contact
- dp@metalinxx.ioResearch inquiries