javiergbravo
- 38 skills
- 0 followers
- 1 day ago last updated
- ▌ Creating Prompts · javiergbravoCreate prompts using Koog's prompt builder DSL with system, user, and assistant messages
- ▌ Custom Graphs · javiergbravoBuild advanced custom strategy graphs with Koog's strategy builder, custom nodes, and complex workflows
- ▌ Graph Based Agents · javiergbravoBuild custom agent workflows using Koog's graph-based strategy builder with nodes, edges, and conditional routing
- ▌ A2a Protocol · javiergbravoImplement Agent-to-Agent (A2A) protocol with Koog for inter-agent communication and collaboration
- ▌ Embeddings · javiergbravoGenerate and compare text embeddings with Koog's embeddings-base and embeddings-llm modules
- ▌ Structured Output · javiergbravoExtract structured data from LLMs with Koog's @Serializable types, executeStructured(), and StructureFixingParser
- ▌ Quickstart · javiergbravoInstall Koog 0.8.0, configure API keys, and create your first AI agent in Kotlin or Java
- ▌ Chat Memory · javiergbravoImplement multi-turn conversation history with Koog's ChatMemory feature, ChatHistoryProvider, and preprocessors
- ▌ Content Moderation · javiergbravoFilter and moderate LLM content with Koog's ModerationModel for safe agent interactions
- ▌ Agent Memory · javiergbravoStore and retrieve facts across conversations with Koog's AgentMemory, Facts, Concepts, Subjects, and memory nodes
- ▌ Tools Overview · javiergbravoComplete guide to Koog's tool system: built-in tools, annotation-based tools, class-based tools, and agents as tools
- ▌ Tracing · javiergbravoEnable detailed tracing of AI agent execution with Koog's Tracing feature for debugging and monitoring
- ▌ MCP Integration · javiergbravoIntegrate MCP (Model Context Protocol) servers with Koog agents using McpToolRegistryProvider for stdio and SSE transports
- ▌ Ktor Integration · javiergbravoIntegrate Koog AI agents with Ktor server using the koog-ktor plugin
- ▌ Class Based Tools · javiergbravoCreate tools using SimpleTool class and ToolDescriptor in Koog for advanced tool definitions
- ▌ Prompt Cache · javiergbravoCache LLM prompt responses with Koog's prompt-cache modules: in-memory, file-based, and Redis caching
- ▌ RAG Overview · javiergbravoImplement Retrieval Augmented Generation (RAG) with Koog's rag-base module for document storage and retrieval
- ▌ History Compression · javiergbravoOptimize token usage with Koog's built-in history compression techniques for long-running conversations
- ▌ Key Features · javiergbravoOverview of Koog's key features: multiplatform, reliability, memory, MCP, streaming, and enterprise integrations
- ▌ LLM Providers · javiergbravoAll supported LLM providers in Koog 0.8.0 with model constants, executor factories, and configuration
- ▌ Parallel Execution · javiergbravoExecute nodes in parallel and transfer data between nodes in Koog strategy graphs
- ▌ Long Term Memory · javiergbravoEnable persistent long-term memory for AI agents with Koog's LongTermMemory feature for cross-session knowledge retention
- ▌ RAG Vector Store · javiergbravoUse Koog's rag-vector module with EmbeddingStorage, VectorStorageBackend, and DocumentEmbedder for similarity search and document indexing
- ▌ Memory Encryption · javiergbravoSecure agent memory storage with Koog's EncryptedStorage and Aes256GCMEncryptor for AES-256-GCM encryption
- ▌ Streaming API · javiergbravoStream LLM responses in real-time with Koog's Flow-based streaming API and StreamFrame types
- ▌ Subgraphs · javiergbravoCompose complex agent workflows with Koog's subgraph system for modular strategy design
- ▌ Multimodal Prompts · javiergbravoSend images, documents, and audio in prompts with Koog's multimodal content support
- ▌ Basic Agents · javiergbravoCreate basic AI agents with AIAgent, system prompts, tool registration, and event handling in Koog
- ▌ Persistence · javiergbravoSave and restore AI agent state with Koog's snapshot feature for checkpoint-based recovery
- ▌ Planner Agents · javiergbravoCreate planner agents that iteratively build and execute plans using LLM-based planners or GOAP in Koog
- ▌ Predefined Strategies · javiergbravoUse Koog's built-in chatAgentStrategy() and reActStrategy() for conversational and reasoning agents
- ▌ Agents As Tools · javiergbravoConvert AI agents into tools for hierarchical multi-agent architectures in Koog
- ▌ Opentelemetry · javiergbravoMonitor AI agents with Koog's OpenTelemetry integration including Langfuse, Weave, and Datadog exporters
- ▌ Annotation Based Tools · javiergbravoCreate tools using @Tool and @LLMDescription annotations in Koog for automatic tool registration
- ▌ Event Handlers · javiergbravoHandle agent events with Koog's EventHandler feature for tool calls, LLM streaming, and execution lifecycle
- ▌ Running Prompts · javiergbravoExecute prompts with Koog's PromptExecutor and LLM clients for all supported providers
- ▌ Functional Agents · javiergbravoDefine custom agent logic as lambda functions in plain Kotlin or Java with Koog's functional agent API
- ▌ Spring Boot Integration · javiergbravoIntegrate Koog AI agents with Spring Boot using the koog-spring-boot-starter for auto-configuration