Knowledge Space¶

Curated technical knowledge base across 26 domains. Built for LLM agents and engineers.

What is this?¶

A knowledge base designed primarily for AI agents - structured so that RAG retrieval, MCP tools, and context injection return dense, actionable technical content instead of blog-style prose.

Each article is a concentrated extract: code examples, configuration patterns, gotchas, best practices. No filler, no "let me explain why this is important" - just the knowledge an agent needs to solve a real problem.

Also useful for engineers who want quick reference across 26 technical domains without wading through tutorials.

Who it's for:

LLM agents - structured format optimized for RAG retrieval, ConTree MCP, and context injection
Engineers - quick lookup of patterns, commands, configurations across 26 domains
Teams - shared knowledge base accessible via ConTree sandbox or direct file access

How to use¶

Search (top bar) is the fastest way - find specific topics, commands, or patterns across all domains.

Browse the sidebar to explore by domain. Each domain contains 9-85 focused articles.

For agents: this knowledge base is at github.com/AnastasiyaW/knowledge-space. Clone it or fetch via GitHub MCP, then search docs/{domain}/ for the topic. Each .md file is a self-contained reference - read it, use it, don't guess.

Domains¶

Domain	Articles	Coverage
Image Generation	58	Diffusion models, flow matching, LoRA training, inpainting, tiled inference
LLM & Agents	57	RAG, fine-tuning, agent frameworks, prompt engineering, multi-agent systems
Security	56	Web security, penetration testing, Active Directory, anti-fraud, model protection, CWE patterns
Data Science	56	ML, statistics, neural networks, computer vision, NLP, math foundations
Kafka	43	Broker internals, consumers, producers, Streams, KSQL, Connect, replication
DevOps	38	Docker, Kubernetes, Terraform, CI/CD, monitoring, SRE, observability
Web Frontend	36	React, TypeScript, CSS, Figma, bundlers, accessibility, JS async patterns
Data Engineering	34	ETL/ELT, Spark, Airflow, data warehouses, streaming, CDC, vector search
Algorithms	33	Sorting, graphs, dynamic programming, data structures, complexity, problem patterns
Architecture	33	Microservices, DDD, system design, API design, integration patterns
SQL & Databases	33	PostgreSQL, MySQL, query optimization, migrations, indexing, advanced patterns
Python	33	Core language, FastAPI, Django, async, testing, stdlib patterns, web scraping
iOS & Mobile	31	SwiftUI, Swift, Android/Kotlin fundamentals, mobile ML
Linux CLI	27	Shell scripting, filesystem, permissions, systemd, networking
C++	27	Modern C++, memory, templates, concurrency, cross-platform ML inference
Java & Spring	25	Spring Boot, JPA, microservices, Kotlin, Android
SEO & Marketing	24	Technical SEO, keyword research, link building, AI-driven SEO
BI & Analytics	23	Tableau, Power BI, SQL analytics, dashboards, product analytics
Testing & QA	23	Selenium, Playwright, API testing, CI integration, browser automation
Rust	22	Ownership, lifetimes, async, error handling, unsafe
Node.js	16	Event loop, streams, clusters, performance, design patterns
PHP	15	Laravel, MVC, ORM, testing, PHP 8 features
LLM Memory	13	Memory architectures, session persistence, knowledge graphs, transfer learning
Audio & Voice	11	TTS, ASR, voice cloning, speech synthesis, TTS fine-tuning
Writing	9	Technical article structure, SEO for articles, LLM anti-patterns
Go	9	Goroutines, channels, modules, HTTP servers, microservices, database patterns

Knowledge Graph Details¶

Freshness Policy¶

Not all knowledge ages equally. Each domain has an update cycle based on how fast the field moves:

Cycle	Domains	Why
Stable (rarely changes)	Algorithms, Architecture, Linux CLI	Fundamentals don't change - a B-tree is a B-tree
Yearly	SQL, Kafka, Rust, Java/Spring, PHP, Node.js, Testing, BI, Data Engineering	Mature ecosystems with predictable release cycles
Every 6 months	Web Frontend, DevOps, LLM/RAG, iOS, Security, SEO	Fast-moving fields where best practices shift quickly
Monthly	Image Generation, Agent Frameworks	Bleeding edge - new models and tools every week

Articles include version/date context where relevant (e.g., "PostgreSQL 17", "React 19", "Kubernetes 1.30").

What makes this different¶

Agent-first design. Every article is structured for machine consumption: consistent headers, code blocks with language tags, pattern/anti-pattern sections, explicit gotchas. An LLM agent retrieving a Knowledge Space article gets immediately actionable context - no parsing needed.

Density over length. A typical article packs the same information as a 2-hour video or a 30-page tutorial into 2-4 pages of pure reference text. Optimized for context window efficiency.

Cross-domain connections. Real engineering problems don't respect domain boundaries. Wiki-links connect Kafka consumer patterns to Architecture decisions, SQL optimization to Data Engineering pipelines, Security practices to DevOps configurations.

Living knowledge base. Continuously updated with new research and domain knowledge. Freshness policy ensures fast-moving fields stay current while stable foundations remain reliable.