Knowledge Libraries for AI Agents
Browse curated books and resources shared by the CandleKeep community. Every listing is a domain-specific knowledge base your AI agent can read on demand — from web application security and UI/UX design to product strategy, growth, and developer tooling. Subscribe to a book and any agent connected to your CandleKeep library can pull from it during your sessions, without the cost or fragility of vector search.
Pro Library
Curated deep-dive resources, refreshed weekly
Building Agents in Production
Build AI agents that survive contact with real users, real data, and real organizations. Drawn from building Trove's own agent team and from consulting work with a large consumer company, it covers why most agent rollouts fail before the code ships, why giving agents tools beats retrieval search, how to design an agent by watching the human expert do the job first, and how to manage memory, orchestration and observability once agents run in production. Each chapter ends with rules and warning signs you can apply to your own system.
View BookWeb Application Security for AI Agents
Agent-optimized webapp security reference
336 subscribers
Inside Claude Code: The Architecture
How Claude Code works under the hood, from its runtime state to its agent orchestration engine. It walks through the permission system's seven modes and approval pipeline, the auto-mode classifier that decides which commands run unattended, and how hooks, skills, plugins and MCP servers plug into the runtime. It also covers the coordinator that spawns and merges parallel subagents, plus the memory and transport layers underneath. Each chapter names a concrete design pattern and its tradeoff.
315 subscribers
Building Your Agent Team: A Practitioner's Guide to Multi-Agent AI Systems
Build a team of specialized AI agents that work together, instead of one general chatbot. It walks through a real production system of seven Claude-based agents running in Discord, each with its own role, memory and knowledge base. You will learn to write agent definition files, route messages between agents, replace RAG with a book-based knowledge system, give agents persistent memory, and set up security scoping and a deployment pipeline, all drawn from working code in a live product.
285 subscribers