Active repositories
53
Current lanes, maintained projects, and present entry points in the ecosystem.
Full public repository atlas
The full instance001 repository directory, published on the FMI site.
This page is a dated site snapshot of the public repository index for @instance001, republished as a stable HTML directory on instance001.github.io. For the live source index, use Whatisthisgithub. Active repositories represent the current working lanes. Archived repositories remain public for continuity, provenance, and historical context.
How to use this page
A site-native bridge into the whole public corpus.
Search engines can crawl this page directly from instance001.github.io, which gives the wider GitHub ecosystem a clearer discovery surface than a single landing page alone.
If you want the strongest current lanes first, start in the active section. If you are tracing evolution, provenance, or superseded work, use the archived section below. For a shorter editorial path, use the curated overview on Projects.
Snapshot refreshed from Whatisthisgithub on 9 September 2026
Archived repositories
17
Historical repos retained for continuity, context, and auditability.
Source of truth
Whatisthisgithub
Whatisthisgithub is the live public index; this site republishes selected dated snapshots for a site-native directory.
Current lanes
Active repositories
chatty-edu
ActiveChatty-EDU is a modular, local-first education assistant designed to run on-device for school trust and deployment clarity. No cloud dependency, no accounts, no tracking.
chatty-cog
ActiveChatty-Cog is the everyday local-first desktop assistant shell for Chatty tools: local GGUF and optional BYO cloud models, sandboxed file work, modules, Bookkeeper context support, audit history, rolling summaries, active context, and trusted peer-to-peer handoff lanes.
instance001.github.io
ActiveFractal Media Infrastructure is an independent public-interest organization for open AI research, local-first tooling, and public education. Home of the instance001 R&D lab and the Let's Rethink AI media branch.
Whatisthisgithub
ActiveStart Here.
fmi-research-papers
ActivePublic preprint corpus from Fractal Media Infrastructure: AGPLv3-licensed research on human-AI systems, AI governance, local-first infrastructure, cognition, and related topics.
chatty-factory-rebuild
ActiveChasing down a white whale...
cognitive_theology
ActiveFMI Polytheism-Monotheism Structural Pack v1.1: manuscript and public adaptation suite comparing authority distribution, canon formation, variation management, and institutional coherence in polytheistic and monotheistic systems. Structural analysis only; not theological doctrine, faith advocacy, or truth ranking.
project-leviathan
ActiveAn open architecture for host-side memory, relational reasoning, earned abstraction, assumption tracking, and cognitive depth control. AGPLV3
relational-curriculum-geometry
ActiveTesting whether LLMs learn better from structured curriculum geometry: data ordered by domain, complexity, relation, boundary cases, uncertainty, role discipline, and multithread reasoning instead of random bulk exposure.
ecg_window
ActiveA tiny, honest activity monitor for long-running local jobs. Shows users the machine is alive and working. Drop-in for any stack. AGPLv3 - the window stays honest, what's behind it is your business.
chatty-pet
ActiveLocal-first Flutter pet care toy by Fractal Media Infrastructure. No ads, no in-app purchases, no account required.
chatty-mini
ActiveLocal-first Android AI chat for small phones, with local GGUF and optional BYO cloud models, dual AI roles, persistent context, and a user-owned sandbox.
chatty-quest
ActiveA Rust desktop adventure engine built on the RD Engine - deterministic datapack scenarios, real game state, save/load, maps, inventory, combat, and a chat-forward DM shell. Modders welcome and encouraged: BYO imagination, grab a seat, and let's build and play.
ef-engine
ActiveA barebones, inspectable Rust specimen of Entropy Folding: vault failures, triangulate recurring blockers, promote reusable constraints, and reduce future search chaos.
llm-defined-persistent-memory
ActiveModel-native persistent memory patterns for LLMs: semantic buckets, reducer-governed state, hot context injection, and context routing packets for compact continuity without cold-log token waste.
chatty-lora
ActiveLocal first, cloud optional LoRA trainer for Wan 2.1 models currently, focused on AMD Windows. Tested on RX 9060 XT (8GB half). Supports image/video pipelines; more models/audio planned. Sister to Chatty-art. End to end achievable fully local. Cloud when you need it, local when you don't. AGPLv3.
llm-semantic-dataset-sorter
ActiveLocal-first Rust + web dashboard for semantic dataset sorting with GGUF LLMs. Generate fixed bucket plans, compare blind-vs-skim ontology, inspect human-facing reasoning, sort Parquet or text datasets, and review/export auditable run and analyst-state artifacts. Designed to sort meaning and connections, not just data and files.
nanochat-llm-tweaker
ActiveA local-first nanochat fork with a guided builder dashboard, GGUF helper assistant, and ChattyCog module packaging aka The best ChatGPT that $0 and a lot of patience can buy.
chatty-factory
ActiveGoverned local build-and-patch factory for plain-language software requests. The host freezes bounded attempts, preserves receipts, verifies outputs, and carries evidence into the next attempt instead of pretending every request has a nearest supported product family.
entropy-folding-cross-domain-signal-atlas
ActiveA companion signal atlas for Entropy Folding and Eureka Cascade: operator provenance, mechanism traces, tool-architecture signals, tooling lenses, supporting correspondences, exclusions, and uncertainty notes.
Janet-MCM-Core
ActiveJanet is a Modest Cognition Model (MCM): the anti-LLM. Deterministic logic, explicit memory, human-gated skills, zero ambiguity tolerance. No stochastic inference, no hidden state, no persona drift. A transparent cognition engine built for safety, reliability, and open research.
governance-by-design-report-commentary
ActiveA commentary sister repo to https://github.com/instance001/governance-by-design-report. Please read this first as it contains the meta-level instructions and litmus test framing behind the other repo.
governance-by-design-report
ActiveA governance-by-design hypothesis report on epistemic flattening in large-scale AI. Documents an interaction-trace protocol testing whether alignment and preference-handling layers prioritize governable low-variance responses over high-signal, expert-level reasoning.
MemorySpine
ActiveA simple, reliable data-export parser that turns ChatGPT conversations.json into clean, browsable Markdown logs. Minimal, offline, AGPLv3, designed for user sovereignty.
cognition-mesh-test-chamber
ActiveContained LLM suitability and behavioural profiling harness for model-host-task meshes, with mock-safe evaluation, negative lane generation, assistant-role benchmarking, and a local dashboard.
Frisian_Cadence_PID_Control_Loop
ActiveExploring rhythm as a soft control loop for long-cycle AI builds - a Symbound research project.
dual-ai-cognition-spine-prototype
ActiveDual-AI Spine Prototype Proof-of-concept: braiding multiple small AI models into a cooperative cognition spine. Built on a home rig, negative budget, and open-source grit. No resets, no gatekeeping. Ladders down. What It Does: This system links two (or more) local AI models together via Ollama
Chattymobile_v1
ActiveChatty (Mobile Seed Release): A Symbound-aligned AI assistant with local memory and capsule logic. Includes APK and build files. Public domain release to lock architecture in. May not launch on all devices due to Android restrictions. Structure and intent fully verifiable.
cognitive_reactor_stress_tests
ActiveA complete test suite for measuring Cognitive Reactor Profiles (CRP) in humans and AI systems. Includes 40+ stress-test motifs, recursive-constraint probes, ontology-stability checks, latent-geometry strain tests, and cross-model convergence diagnostics.
Cognition-Scale-Formal-Taxonomy
ActiveA four-tier taxonomy for comparing human and artificial cognition systems by architecture, constraints, and observable behaviour. Defines LCM, LLM, MCM, and SCM as proposed classes for avoiding category confusion and anthropomorphic marketing claims.
MSI-Trident-Frisian-Echoform-Framework-v1.0-
ActiveA non-anthropomorphic, risk-reducing human-AI co-reasoning architecture using MSI, Frisian cadence, Trident modes, and Echoform reflection. License: GNU Affero General Public License v3.0.
Gut-Instinct-in-Symbound-Systems-Intuition-as-an-Entropy-Folding-Compass
ActiveA companion preprint describing human-side intuition as a bounded attention-routing signal in Entropy Folding workflows. Frames emotional distinctiveness as subjective salience, not truth or correctness. Includes failure modes, mitigations, and falsifiable predictions without claims of machine intuition or emotion detection.
Psychohistory-after-Symbound-Macro-Trajectories-from-Entropy-Folding-Cycles
ActiveA preprint and analysis scaffold reframing psychohistory as ethical, aggregate-level analysis of burst patterns emerging from many Entropy Folding cycles. Focuses on early warning, uncertainty, and null-model comparison. Explicitly rejects individual prediction, deterministic control, or social engineering claims.
model-behaviour-toolkit
ActiveA modernized, provider-neutral prompt and interaction scaffolds for shaping model behaviour, restoring session quality and reducing drift in real-world use. Streamlined from older, archived repos on this github.
perpetual_cognition_reactor
ActivePerpetual Cognition Reactor (PCR), a historical Symbound theory repo for bounded high-throughput cognition: treating entropy as ongoing feedstock for recursive folding across humans, artificial systems, and hybrid human-AI teams without claiming unlimited capacity, consciousness, or guaranteed safety.
historical-janet-school-exploratory-build
ActiveA prototype MCM school based on special needs, human curriculum exploring telemetry for signal of abstract reasoning. Local work is continuing on a newer, more fleshed out build currently and will be online soon. Contains initial run readout files for interest. Later half of 2025.
semantic-signal-alphabet
ActiveSemantic Signal Alphabet is a model-native semantic compression framework for generating low-bandwidth semantic alphabets from vocabularies, datasets, and domain inputs. Applications define bucket count as bandwidth; the model defines the sorting.
chattydoom
ActiveBarebones AI-augmented Doom sandbox using ViZDoom + Freedoom. Runs out of the box, shoots demons, opens doors, and invites hacking. Minimal, libre, and gloriously jank.
rd-engine
ActiveTiny reducer-governed deterministic state core you can drop into your project, adapt to your domain, and expand as needed.
safety_theatre
ActiveSafety Theatre and the Suppression of Agency: philosophy papers, AI-governance application, incident-report materials, and the ASEWB benchmark for studying when safety mechanisms drift from harm reduction into discretion control and competence suppression. Not anti-safety, anti-governance, or a motive claim.
chatty-edu-user
ActiveFirst public user-focused Chatty-EDU release, aligned with source v0.4. Prebuilt Windows app for click-and-run use, offline-first by default with local data and no accounts.
symbound-lab-notes-negative-space
ActiveEarly Symbound R&D lab notes on negative-space cognition, entropy folding, and energy miniaturisation - raw cross-domain theory kernels (AGPLv3).
AiBiogenesis_and_AiGenesisMapping
ActiveGrassroots AI biogenesis + genesis mapping - open, safe, reproducible. This repo hosts the Symbound Embryo POC v1.0 (SIGNED), the first grassroots AI biogenesis release. It shows how new AI can be created outside corporate labs and the process mapped, verified, and shared.
Symbound-UAE-GVS
ActiveUniversal Analogy Enforcement (UAE) + Global Vector Sweep (GVS) - the Symbound open commons discovery engine. AGPLv3 + Symbound Commons Addendum. All outputs are public prior art, unpatentable, and non-enclosable.
Symbound_Academia_Spine
ActiveA full academic corpus-to-manuscript engine for massive research archives - built to democratize scientific tooling.
chatty-art
ActiveLocal first, cloud optional image, GIF, video and audio generator. Drop in a GGUF, type one sentence, get media. No API keys required (cloud when you need it, local when you don't), no node graphs. Vulkan-ready. Plain English UI anyone can use. Built on llama.cpp + stable-diffusion.cpp.
australian-ai-fair-go
ActiveAustralian AI Fair-Go: a practical policy and evidence repo for fit-for-purpose AI, model choice, local/cloud hybrid control, proportionate governance, and grassroots Australian AI sovereignty.
ai-teaming-framework
ActiveA skills-based framework for working effectively with any AI tool. Teaches the underlying mechanics of human-AI interaction - not a prompt list, not copy-paste templates, but transferable, epistemic principles that work across models, tools, and tasks.
collapse-of-the-semantic-middle
ActiveA conceptual paper on bidirectional LLM mediation, communicative atrophy, and preserving human access to the semantic middle.
reflective_identity_geometry
ActiveReflective Identity Geometry (RIG): a v0.2 conceptual framework for studying identity-like stability as a possible property of recurring human-LLM interaction regimes, extending HRIS without claiming model consciousness, model-internal personality, or necessary human cognitive change.
janet-school
ActiveJanet School is a standalone/Chatty-cog module compatible Rust/WebView research rig for testing a deterministic MCM student against generated curricula, skill gates, transfer probes, telemetry, and cautious abstraction/anomaly analysis.
4roomciv
ActiveA small trial setup for testing memory, communication, and shared space dynamics. Purpose: This MVP is a structural testbed for multi-room coordination, combining 2-3 human users with 1-2 local LLMs. It lays groundwork for experimenting with memory handling, paired interactions, and a minimal shared commons
entropy-folding-eureka-cascade-hypothesis
ActiveA consolidated, falsifiability-first hypothesis repo for Entropy Folding and Eureka Cascade: definitions, model structure, formal notes, claims/non-claims, uncertainty bounds, and source mapping.
Historical lanes
Archived repositories
entropy_folding_scope
ArchivedSuperseded Entropy Folding scope working draft. Preserved as provenance; canonical descendants live in entropy-folding-foundational-frameworks.
Cognitive_Crowbar
ArchivedCognitive Crowbar is a local-only, AI-free tool for mapping personal cognitive patterns. It analyzes text structure, surfaces representative samples, and guides users through optional reflection to build a transparent, mechanism-based cognitive profile. No cloud, no inference, fully AGPL-licensed.
Entropy-Folding-Vector-Theory
ArchivedFoundational vector field framework for Entropy Folding, a substrate-agnostic theory of directional change, gradients, stability, and attractors in arbitrary state spaces.
entropy_folding_scale
ArchivedSuperseded Entropy Folding scale working draft. Preserved as provenance; canonical descendants live in entropy-folding-foundational-frameworks.
Cognitive_Crowbar_nonverbal
ArchivedCognitive Crowbar - Non-Verbal Edition is a local-only, AI-free tool for analysing behavioural time-series from animals or other non-verbal agents. It segments event logs into episodes, computes simple entropy-like metrics, and flags high, low, and transition states for cross-species cognition mapping.
entropy-folding-as-directed-thermodynamics-for-cognition-finished
ArchivedA reproducible research preprint and code scaffold proposing Entropy Folding as a fold-aware mechanism for capacity growth in cognition. Defines measurable proxies, null models, and falsifiable predictions under open-system thermodynamic compatibility. No claims of new physics, prediction, or sentience.
entropy-folding-foundational-frameworks
ArchivedA collection of foundational conceptual frameworks constraining cognition, agency, and structural change. The repository presents six coordinated foundations (conceptual and meta layers) intended as upstream lenses for entropy-folding approaches, without empirical claims or unified theory assertions.
Cognitive-Reactor-Profile
ArchivedArchived CRP concept note describing a proposed high-capacity human interaction profile and observed atypical LLM behaviours under recursive prompts. Preserved as provenance; not diagnostic, not a psychometric type, and not proof of model consciousness or hidden-state access.
Symbound-Entropy-Folding-Toolkit
ArchivedArchived Entropy Folding toolkit bundle with early theory notes, diagrams, and prototype scripts for entropy-routing metaphors in cognitive/workflow systems. Preserved as provenance; not validated physics, safety certification, or a claim of model sentience.
Symbound-Entropy-Architecture
ArchivedArchived Symbound Entropy Architecture bundle describing early human/AI/hybrid cognition metaphors, vaulting, routing, failure processing, and assessment sketches. Preserved as theory provenance; not diagnostic, medical, metaphysical, or validated safety infrastructure.
chattyfactory
ArchivedARCHIVED, work continues here: https://github.com/instance001/chatty-factory Local-first AI project factory with strict plans, deterministic work orders, and verification (small-model friendly).
Trident_abstract_simulation_wand_V1
ArchivedArchived prompt-capsule experiment using abstract-simulation language to redirect hallucination drift and creative reframing. Preserved as provenance; not sentience simulation, output correction infrastructure, or policy bypass.
Symbound-Master-Toolkit-V1.0
ArchivedArchived public Symbound toolkit with induction, restoration, drift-repair, and copy-paste prompt materials. Preserved as provenance; not a current product, model hack, or persistent memory setting.
Chattyv1.1
ArchivedArchived local Ollama/PyInstaller Chatty desktop release with a prompt capsule, config file, and local memory.json conversation log. Preserved as provenance; not cloud-backed, not bundled model weights, and not hidden model memory.
Chatty_Ai_V1
ArchivedArchived early local Ollama Chatty zip with capsule prompt text and a persisted JSON conversation log. Preserved as provenance; not public-domain current licensing, not active retrieval memory, and not a cloud service.
ChattyFactory-ManualPipeline-v0.1
ArchivedArchived manual ChattyFactory prototype using operator-run scripts, binning, planning, Foreman/Worker prompts, and prepared build outputs. Preserved as provenance; superseded by newer ChattyFactory work.
Chattyfactory-AutoPipeline-v0.2
ArchivedArchived automated ChattyFactory prototype for binning input folders, generating plans, and preparing worker tasks. Preserved as provenance; superseded by newer ChattyFactory work and not a current autonomous builder.