Pixi Wiki turns my notes, project docs, research, and working context into structured, maintained knowledge bases. Humans browse them like a wiki. Agents read them natively as plain Markdown with llms.txt and local MCP access.
$ curl https://pixiiidust.github.io/pixi-wiki/llms.txtUse llms.txt as the first routing map, then follow links to raw Markdown, namespace files, or MCP setup.
Agent Operations
Hermes, crew workflows, traces, and quality gates for running agents well.
Pixoid/Tinker/Quill/Boba operating model, Hermes Mission Control, route governance, memory boundaries, context handoffs, Knowledge Pack Routing, agent entrypoint meshes, static retrieval/eval gates, self-improving agent systems, effective-state-load boundaries, and workflow reliability practices.
Workflow, agent, and model-behavior evaluation; traces; context-overfitting detection; reliability metrics; evidence gates; style-transfer checks; and quality read-outs.
Hermes Agent setup and configuration, MCP integration, profiles, skills, memory, cron, gateway operations, subagents/delegation, session traces, trajectory capture, batch evals, Langfuse traces, NeMo Relay ATOF/ATIF exports, capability-routing decisions, and Jamie-specific operating reference for Pi
Knowledge Systems
The wiki/compiler layer, local retrieval, infrastructure, curated source/data readiness, and systems for distributing useful knowledge.
Vault architecture, Wiki Compiler Maps, AgentWikis compatibility, namespace compiler logic, source/output repo boundaries, and pixi-wiki publication model.
Long-form attention architecture, honest packaging, narrative/explanation structure, audience retention, shareable payoff design, cross-format translation across video, Substack/blog essays, X articles/threads, and measurement boundaries between entry, retention, redistribution, understanding, and t
Dataset/source curation for LoRA/fine-tuning, provenance, scraping/source inventories, corpus readiness, dataset-recipe publication, and LKY Brain as a completed example.
Local-first AI setup, local LLMs, LoRA/fine-tuning infrastructure, RAG over compiled wikis, deterministic local workflow offload, and hardware/software constraints.
Labs & Product Surfaces
AI-native products, simulations, demos, and experiment-facing project labs.
AI-native product/application surfaces, problem framing, product demos, PM case studies, product-management system-steering frameworks, side-quest validation, AI-era judgment and taste, role-aligned deployed portfolio proof, side-door opportunity and public-proof synthesis, J-Space-Replay, LKY Avata
PufferLib/RL projects, Critical Ranger FFM, zone-control experiments, simulation evidence gates, environment design, and future similar RL labs.
Other Wikis
Additional namespaces that do not yet fit one of the main shelves.
The `pattern-language` namespace covers the abridged, hyper-textual pattern corpus from `apl-md`: 253 built-environment patterns, their Problem/Solution framing, related-pattern graph, provenance, license guardrails, and agent-facing retrieval guidance for spatial design and worldbuilding.
The `software-architecture-metapatterns` namespace covers software architecture metapatterns: system topologies, layers, services, pipelines, proxies, orchestrators, plugins, hexagonal architecture, service-oriented architecture, polyglot persistence, pattern aliases, architectural forces, dependenc
The `ui-patterns` namespace covers the public UI Patterns pattern catalog structure: pattern titles, source URLs, UI/persuasive taxonomy, section availability, example counts, provenance, copyright boundary, and agent-facing retrieval guidance for product/design review.