Analysis updated 2026-05-18
Upload the AI Systems compiled packs into Claude or GPT so the model can reason about RAG and agent design with domain depth.
Use the Macroeconomics or Game Theory canons as background knowledge for an AI assistant helping with investment or strategy decisions.
Ingest the Automotive Systems guide into a project knowledge base to improve an AI's vocabulary for vehicle diagnostics and repair.
| stunspot/stunspots-guides | abderazak-py/retro-homepage | arthurmoorgan/drift | |
|---|---|---|---|
| Stars | 6 | 6 | 6 |
| Language | — | HTML | JavaScript |
| Setup difficulty | easy | easy | moderate |
| Complexity | 1/5 | 2/5 | 2/5 |
| Audience | developer | ops devops | general |
Figures from each repo's GitHub metadata at analysis time.
Stunspot's Guides is an index repository that links to 11 separate knowledge canons, each covering a different subject domain. The guides are written primarily for AI systems: the text is structured so that language models, RAG pipelines, and agent memory layers can ingest them and gain dense, domain-specific knowledge. Human readers can use them as field manuals, but the stated purpose is to give AI systems stable terminology, reasoning frameworks, and practical heuristics for a given topic. The 11 guides span a wide range of subjects, including AI systems design, macroeconomics, game theory, automotive systems, human behavioral neurobiology, business venture formulation, sales prospecting, legal reasoning, gastronomic engineering, semantics and semiotics, and investigative news intelligence. Each guide lives in its own GitHub repository and is organized into compiled knowledge packs, per-report source files, and an omnibus bundle for single-file import into long-context AI systems. The quickstart is simple: pick a subject, download three to five compiled packs from that guide's repository, upload them to an AI assistant's project knowledge base or paste them into a chat, then talk to the model about the topic. The index repository acts as a navigation hub with links to each guide's repo and a machine-readable manifest listing all available canons. This repo itself contains no code. It is pure documentation: a catalog, usage instructions, and a JSON manifest. The guides are licensed under Creative Commons Attribution 4.0, meaning you can use, share, or build on them as long as you credit the author. RAG stands for retrieval-augmented generation, a technique where an AI model draws on a provided knowledge base instead of relying solely on what it learned during training.
An index of 11 Markdown knowledge canons on subjects like AI systems, macroeconomics, and game theory, designed to be uploaded into AI assistants as project knowledge for richer domain reasoning.
Use, share, or build on these guides for any purpose as long as you credit the original author (CC BY 4.0).
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.