# jetbrains/koog **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/jetbrains-koog).** 3,735 stars · 322 forks · Kotlin · apache-2.0 ## Links - GitHub: https://github.com/JetBrains/koog - Homepage: https://docs.koog.ai - awesome-repositories: https://awesome-repositories.com/repository/jetbrains-koog.md ## Topics `agentframework` `agentic-ai` `agents` `ai` `ai-agents-framework` `aiagentframework` `android-ai` `anthropic` `genai` `generative-ai` `java` `jvm` `kotlin` `ktor` `llm` `mcp` `multi-agent-systems` `ollama` `openai` `spring` ## Description Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project covers a broad range of capabilities, including multimodal data processing, OpenTelemetry-based observability, and schema-driven structured output enforcement. It provides comprehensive tool integration for browser automation and filesystem management, along with conversation history compression and state-checkpoint persistence. The library is designed for JVM framework integration and supports multiplatform agent deployment. ## Tags ### Artificial Intelligence & ML - [AI Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/ai-agent-orchestrators.md) — Provides a comprehensive system for organizing and coordinating specialized agents using structured workflows and tool interactions. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [Agentic Workflow Graphs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-graphs.md) — Implements agent behaviors as directed graphs of tasks and state transitions to orchestrate complex workflows. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [Autonomous Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-orchestration.md) — Provides a framework for designing and deploying autonomous agents that execute complex workflows via directed graphs. - [Model Provider Management](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-management.md) — Provides a central orchestrator for managing multiple LLM providers with dynamic switching and unified execution. - [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Provides persistent storage mechanisms for agents to recall information and context across different sessions. ([source](https://docs.koog.ai/features/index.md)) - [Agent State Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-state-persistence.md) — Saves and restores the full execution state of autonomous agents to enable session recovery and rollbacks. ([source](https://docs.koog.ai/index.md)) - [Agentic LLM Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-llm-frameworks.md) — Provides a comprehensive framework for building autonomous agents that combine LLMs with tool-based workflows and memory. - [Agentic Reasoning Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-reasoning-loops.md) — Implements iterative loops where the agent alternates between reasoning and tool execution to process complex tasks. ([source](https://docs.koog.ai/predefined-agent-strategies/index.md)) - [Agentic State Machines](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-state-machines.md) — Models agent logic as a state machine where nodes represent actions and edges control the flow of data. ([source](https://docs.koog.ai/agents/graph-based-agents/index.md)) - [Stateful Workflow Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/human-in-the-loop-workflows/stateful-workflow-persistence.md) — Stores and updates data across multiple executions of a single node using thread-safe wrappers for state persistence. ([source](https://docs.koog.ai/custom-nodes/index.md)) - [Conversational AI Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-agents.md) — Provides a framework for building agents that engage in interactive, human-like dialogue to assist users and perform tasks. ([source](https://docs.koog.ai/predefined-agent-strategies/index.md)) - [Agent Persona Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/configuration-and-specifications/agent-persona-definitions.md) — Allows the definition of specific system prompts and behavioral constraints to establish agent personas and operational identities. ([source](https://docs.koog.ai/agents/graph-based-agents/index.md)) - [Agent Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-execution.md) — Executes one or multiple tool calls requested by the model, including support for parallel execution. ([source](https://docs.koog.ai/nodes-and-components/index.md)) - [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Interchanges different AI model backends using a unified API without altering core business logic. ([source](https://docs.koog.ai/examples/Attachments/index.md)) - [Tool Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/tool-orchestration.md) — Coordinates the definitions and execution flows of tools between language models and clients. ([source](https://docs.koog.ai/tools/index.md)) - [MCP Server Connections](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/model-context-protocol/mcp-server-management/mcp-server-connections.md) — Establishes connections to context protocol servers using stdio or SSE transports to retrieve remote tools. ([source](https://docs.koog.ai/model-context-protocol/index.md)) - [AI Observability Tracing](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-observability-tracing.md) — Captures execution traces of agent decisions and model interactions using OpenTelemetry spans. - [LLM Tooling Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/llm-tooling-integrations.md) — Connects language models to external APIs and custom functions to enable agents to perform technical tasks. - [Model Request Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/model-orchestration-management/model-request-orchestrators.md) — Manages the execution of prompts to model providers, including streaming and content moderation. ([source](https://docs.koog.ai/ktor-plugin/index.md)) - [Conversation Memory Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-memory-managers.md) — Implements systems for storing and retrieving interaction history to maintain context across multi-turn dialogues. ([source](https://docs.koog.ai/examples/BedrockAgent/index.md)) - [Conversation Flow Design](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-state-management/conversation-flow-design.md) — Uses a structured builder to define the sequence and logic of system and user messages in a conversation. ([source](https://docs.koog.ai/prompts/prompt-creation/index.md)) - [Retrieval-Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-interfaces/retrieval-augmented-generation.md) — Implements a RAG memory system using vector embeddings to provide agents with domain-specific knowledge. - [Conversational Memory Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-memory-systems.md) — Implements a RAG memory system using vector embeddings to maintain long-term conversational context. - [LLM Context Preparation](https://awesome-repositories.com/f/artificial-intelligence-ml/data-preprocessing-pipelines/llm-context-preparation.md) — Prepares the conversation context by adding system instructions and user messages before making requests. ([source](https://docs.koog.ai/nodes-and-components/index.md)) - [External Tool Integration](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integration.md) — Implements capabilities for agents to interact with external APIs and systems to perform technical tasks. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [MCP Protocol Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integrations/mcp-protocol-integrations.md) — Connects agents to external tool registries using the Model Context Protocol via SSE transports. ([source](https://docs.koog.ai/examples/PlaywrightMcp/index.md)) - [Chaining Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/foundation-models/chaining-pipelines.md) — Chains multiple language model requests where the output of one serves as the context for the next. ([source](https://docs.koog.ai/agents/functional-agents/index.md)) - [Tool Result Aggregators](https://awesome-repositories.com/f/artificial-intelligence-ml/function-to-tool-converters/tool-result-aggregators.md) — Processes outputs from executed tools and reintegrates them into the model context for follow-up responses. ([source](https://docs.koog.ai/nodes-and-components/index.md)) - [Hierarchical Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/hierarchical-agent-orchestration.md) — Implements a coordinator agent that manages specialized worker agents to handle multi-domain requests. ([source](https://docs.koog.ai/examples/Banking/index.md)) - [Agent-as-Tool Wrapping](https://awesome-repositories.com/f/artificial-intelligence-ml/hierarchical-agent-orchestration/agent-as-tool-wrapping.md) — Allows agents to be converted into tools, enabling a nested hierarchical architecture for complex task delegation. ([source](https://docs.koog.ai/tools/index.md)) - [Model Context Protocol Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-context-protocol-implementations.md) — Implements the Model Context Protocol to connect agents to remote tool servers for standardized tool access. - [Model Output Formatting](https://awesome-repositories.com/f/artificial-intelligence-ml/model-output-formatting.md) — Enforces structured data schemas to ensure model responses are in a machine-readable format. ([source](https://docs.koog.ai/index.md)) - [Multi-Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-integrations/multi-provider-abstractions.md) — Provides a unified interface to manage multiple AI providers with support for dynamic switching and automatic fallbacks. - [Prompt Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-orchestration.md) — Defines and executes the core prompts that drive interactions between the agent and the language model. ([source](https://docs.koog.ai/index.md)) - [RAG Context Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/rag-context-retrieval.md) — Implements retrieval augmented generation to recall relevant information from vector embeddings across sessions. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [RAG Knowledge Management](https://awesome-repositories.com/f/artificial-intelligence-ml/rag-knowledge-management.md) — Implements a RAG-based memory system using vector embeddings to maintain long-term conversation context across sessions. - [Sequential Agent Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/sequential-agent-execution.md) — Designs sequential subgraphs of nodes and edges to control linear processing of input by agents. ([source](https://docs.koog.ai/glossary/index.md)) - [Agent Communication Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols.md) — Uses a consistent protocol of methods and message formats to standardize interaction between agents and clients. ([source](https://docs.koog.ai/a2a/index.md)) - [Agent Client Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols/agent-client-protocols.md) — Standardizes communication between agents and clients by mapping internal states to protocol blocks. ([source](https://docs.koog.ai/agent-client-protocol/index.md)) - [Agent Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-deployment.md) — Initializes and provisions autonomous agent instances by connecting language models to prompt executors. ([source](https://docs.koog.ai/quickstart/index.md)) - [JVM Backend Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-framework-integrations/jvm-backend-integrations.md) — Embeds agent functionality into existing JVM-based applications through compatibility with common backend frameworks. ([source](https://docs.koog.ai/key-features/index.md)) - [Tool-Based Knowledge Retrievers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-search-tools/tool-based-knowledge-retrievers.md) — Exposes document retrieval systems as tools that agents can invoke on demand for knowledge retrieval. ([source](https://docs.koog.ai/retrieval-augmented-generation/index.md)) - [Node-Level State Transformations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/graph-based-state-orchestrations/node-level-state-transformations.md) — Converts the output of one graph node to match the input type of the next node via state transformations. ([source](https://docs.koog.ai/agents/graph-based-agents/index.md)) - [Parallel Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/parallel-tool-execution.md) — Enables the concurrent execution of multiple tools by an agent to accelerate data gathering. ([source](https://docs.koog.ai/custom-strategy-graphs/index.md)) - [Filesystem Tooling](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/agent-storage-backends/filesystem-backends/filesystem-tooling.md) — Provides tools for agents to perform read, edit, and write operations on the local filesystem. ([source](https://docs.koog.ai/tools/built-in-tools/index.md)) - [Context Trimming](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/conversational-memory-systems/context-trimming.md) — Provides capabilities to reduce token consumption by filtering and trimming conversation history to fit model windows. ([source](https://docs.koog.ai/examples/Chess/index.md)) - [Provider Switching](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/ai-integration-apis/openai-compatible-apis/provider-switching.md) — Changes the active model and toolset mid-conversation while rewriting history to maintain continuity. ([source](https://docs.koog.ai/key-features/index.md)) - [Chat Message Formats](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-message-formats.md) — Organizes instructions using rich text or structured data formats within chat messages. ([source](https://docs.koog.ai/prompts/prompt-creation/index.md)) - [Context Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/context-compression.md) — Reduces the size of message history to prevent exceeding LLM context window limits during long interactions. ([source](https://docs.koog.ai/prompts/index.md)) - [Conversation History Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-management-tools/conversation-history-management.md) — Reduces token consumption by replacing detailed conversation history with concise summaries based on defined strategies. ([source](https://docs.koog.ai/key-features/index.md)) - [Conversation History Extensions](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-history-extensions.md) — Builds new prompts by appending messages to previous conversations to maintain interaction continuity. ([source](https://docs.koog.ai/prompts/prompt-creation/index.md)) - [Execution Interception Hooks](https://awesome-repositories.com/f/artificial-intelligence-ml/execution-interception-hooks.md) — Implements hooks to observe or modify behavior during model calls and agent startup. ([source](https://docs.koog.ai/features/custom-features/index.md)) - [Generation Temperature Controls](https://awesome-repositories.com/f/artificial-intelligence-ml/generation-temperature-controls.md) — Controls creativity and determinism by adjusting the temperature parameter for focused or diverse outputs. ([source](https://docs.koog.ai/model-capabilities/index.md)) - [Human-in-the-Loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-workflows.md) — Implements mechanisms for integrating manual human approvals and interventions into automated agent decision processes. ([source](https://docs.koog.ai/examples/Chess/index.md)) - [Incremental Inference Streaming](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/model-integration-pipelines/model-inference/inference-result-processors/incremental-inference-streaming.md) — Streams model outputs incrementally, including text deltas and reasoning steps, for real-time processing. ([source](https://docs.koog.ai/prompts/llm-clients/index.md)) - [Model Parameters](https://awesome-repositories.com/f/artificial-intelligence-ml/model-parameters.md) — Adjusts randomness, token limits, and output diversity through model parameters to control behavior. ([source](https://docs.koog.ai/llm-parameters/index.md)) - [Provider-Specific Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-management/provider-specific-configurations.md) — Provides advanced configuration options to access provider-specific features like reasoning effort and prompt caching. ([source](https://docs.koog.ai/llm-parameters/index.md)) - [Iterative Response Correction](https://awesome-repositories.com/f/artificial-intelligence-ml/model-response-parsers/iterative-response-correction.md) — Uses an auxiliary model to iteratively fix parsing errors until responses conform to the required schema. ([source](https://docs.koog.ai/structured-output/index.md)) - [Model Fallbacks](https://awesome-repositories.com/f/artificial-intelligence-ml/model-task-retries/model-fallbacks.md) — Automatically redirects requests to a secondary AI provider when the primary client is unavailable. ([source](https://docs.koog.ai/prompts/prompt-executors/index.md)) - [Agent Response Streams](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities/real-time-streaming/agent-response-streams.md) — Streams real-time updates on model responses and tool call lifecycles via an asynchronous event producer. ([source](https://docs.koog.ai/agent-client-protocol/index.md)) - [Multimodal Input Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-input-processors.md) — Ingests and processes diverse data types including text, images, audio, and video for model reasoning. ([source](https://docs.koog.ai/llm-providers/index.md)) - [OpenTelemetry Exporters](https://awesome-repositories.com/f/artificial-intelligence-ml/opentelemetry-exporters.md) — Exports agent lifecycle events and model interactions as traces using the OpenTelemetry protocol. ([source](https://docs.koog.ai/examples/Langfuse/index.md)) - [Prefix Caching](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-caching/prefix-caching.md) — Instructs providers to store prompt prefixes on the server to optimize repetitive workloads. ([source](https://docs.koog.ai/prompts/prompt-creation/cache-control/index.md)) - [Reasoning Capture Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-models/reasoning-capture-utilities.md) — Extracts incremental reasoning text and summaries to reveal the agent's internal thought process. ([source](https://docs.koog.ai/streaming-api/index.md)) - [Provider Failover Handlers](https://awesome-repositories.com/f/artificial-intelligence-ml/sampling-strategies/sampling-provider-fallbacks/provider-failover-handlers.md) — Sends prompts to multiple different model providers to implement fallback logic and ensure reliability. ([source](https://docs.koog.ai/spring-boot/index.md)) - [Structured Prompting Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-prompting-tools.md) — Uses a specialized language to organize system instructions and formatted markdown for consistent prompt structure. ([source](https://docs.koog.ai/examples/Attachments/index.md)) - [Invocation Control Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-use-patterns/invocation-control-strategies.md) — Allows specifying whether the model should automatically choose tools, use a specific tool, or avoid tool use. ([source](https://docs.koog.ai/llm-parameters/index.md)) - [Visual Content Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-content-analysis.md) — Analyzes and extracts insights from image and video content to enable vision-based reasoning. ([source](https://docs.koog.ai/model-capabilities/index.md)) - [Tool Registries](https://awesome-repositories.com/f/artificial-intelligence-ml/workflow-as-a-tool-exposure/agent-as-a-tool-execution/tool-registries.md) — Manages central registries that map tool identifiers to implementations for lookup and invocation by name. ([source](https://docs.koog.ai/tools/index.md)) ### Development Tools & Productivity - [Tool Function Registrations](https://awesome-repositories.com/f/development-tools-productivity/local-function-execution/agent-integrated-functions/tool-function-registrations.md) — Binds a set of available functions to an agent, enabling it to select and execute tools dynamically. ([source](https://docs.koog.ai/examples/Calculator/index.md)) - [Protocol Endpoint Hosting](https://awesome-repositories.com/f/development-tools-productivity/agent-communication-protocol-servers/protocol-endpoint-hosting.md) — Exposes a protocol-compliant endpoint to receive requests, process tasks, and return status updates. ([source](https://docs.koog.ai/a2a/index.md)) - [Context Compression](https://awesome-repositories.com/f/development-tools-productivity/developer-utilities-libraries/workflow-productivity-enhancers/developer-productivity-utilities/developer-utilities/file-resource-management/file-compression-utilities/token-aware-log-compression/context-compression.md) — Reduces token consumption by specifically compressing results from tool executions in the conversation history. ([source](https://docs.koog.ai/examples/Calculator/index.md)) - [Agent Workflow Interception](https://awesome-repositories.com/f/development-tools-productivity/development-workflow/agent-workflow-interception.md) — Provides middleware hooks to intercept and modify the steps of an agent's reasoning loop. ([source](https://docs.koog.ai/features/index.md)) - [Runtime Prompt Modifiers](https://awesome-repositories.com/f/development-tools-productivity/human-in-the-loop-interfaces/interactive-prompts/prompt-editors/runtime-prompt-modifiers.md) — Alters the current prompt object during a session to add, remove, or reorder messages. ([source](https://docs.koog.ai/prompts/index.md)) ### Programming Languages & Runtimes - [Model-Response Routing](https://awesome-repositories.com/f/programming-languages-runtimes/conditional-logic/model-response-routing.md) — Determines the path between graph nodes based on the type of language model response received. ([source](https://docs.koog.ai/agents/graph-based-agents/index.md)) ### Software Engineering & Architecture - [Conditional Branching](https://awesome-repositories.com/f/software-engineering-architecture/conditional-branching.md) — Directs workflow execution paths based on dynamic evaluation of state or tool call detections. ([source](https://docs.koog.ai/custom-strategy-graphs/index.md)) - [Unified Model Interfaces](https://awesome-repositories.com/f/software-engineering-architecture/unified-model-interfaces.md) — Provides a standardized execution interface that abstracts different cloud-based and local language model providers. ([source](https://docs.koog.ai/llm-providers/index.md)) - [Error Recovery](https://awesome-repositories.com/f/software-engineering-architecture/error-recovery.md) — Hooks into workflow failure events to execute custom error recovery and handling logic. ([source](https://docs.koog.ai/features/agent-event-handlers/index.md)) - [Workflow Subgraph Packaging](https://awesome-repositories.com/f/software-engineering-architecture/modular-package-systems/workflow-subgraph-packaging.md) — Provides the ability to group functional nodes into reusable subgraph components for hierarchical logic structures. ([source](https://docs.koog.ai/custom-subgraphs/index.md)) - [Multiplatform Agent Runtimes](https://awesome-repositories.com/f/software-engineering-architecture/multiplatform-agent-runtimes.md) — Runs agent logic on multiple targets using a single multiplatform codebase. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [Performance and Reliability](https://awesome-repositories.com/f/software-engineering-architecture/performance-reliability.md) — Ensures runtime reliability through built-in retries and state restoration from persistence checkpoints. ([source](https://cdn.jsdelivr.net/gh/jetbrains/koog@develop/README.md)) - [Parallel Execution](https://awesome-repositories.com/f/software-engineering-architecture/workflow-nodes/parallel-execution.md) — Executes multiple workflow nodes concurrently to improve performance and aggregate results from parallel paths. ([source](https://docs.koog.ai/custom-strategy-graphs/index.md)) ### User Interface & Experience - [Business Logic Nodes](https://awesome-repositories.com/f/user-interface-experience/visual-node-editors/node-execution-logic/business-logic-nodes.md) — The library defines reusable processing steps with specific input and output types to execute custom business logic. ([source](https://docs.koog.ai/custom-nodes/index.md)) ### Web Development - [Agent](https://awesome-repositories.com/f/web-development/type-safe-clients/tool-definitions/agent.md) — Creates functions with descriptors and type-safe definitions that provide models with metadata to execute external actions. ([source](https://docs.koog.ai/tools/index.md)) - [Browser Automation](https://awesome-repositories.com/f/web-development/web-automation-scraping/web-scraping-automation/browser-automation.md) — Provides capabilities to drive web browsers programmatically for executing tasks and capturing interactions. ([source](https://docs.koog.ai/examples/PlaywrightMcp/index.md)) ### Business & Productivity Software - [Agent Operation Tracking](https://awesome-repositories.com/f/business-productivity-software/task-state-tracking/agent-operation-tracking.md) — Tracks and stores the state, history, and artifacts of long-running operations to provide progress updates. ([source](https://docs.koog.ai/a2a/a2a-server/index.md)) - [Custom Functional Node Development](https://awesome-repositories.com/f/business-productivity-software/workflow-automation/custom-functional-node-development.md) — Supports the creation of specialized functional blocks within a workflow to transform data or interact with models. ([source](https://docs.koog.ai/custom-strategy-graphs/index.md)) ### Data & Databases - [LLM Schema Outputs](https://awesome-repositories.com/f/data-databases/data-governance-modeling/data-modeling-schemas/data-schemas/schema-validated-data-structures/schema-enforced-output-parsers/llm-schema-outputs.md) — Enforces structured JSON outputs from models using schemas and an auxiliary model to correct parsing errors. - [Conversation History Backends](https://awesome-repositories.com/f/data-databases/pluggable-storage-drivers/conversation-history-backends.md) — Integrates pluggable storage backends for persisting and loading conversation records across application restarts. ([source](https://docs.koog.ai/features/chat-memory/index.md)) - [Response Caching](https://awesome-repositories.com/f/data-databases/response-caching.md) — Caches previously executed prompt results to reduce latency and operational costs. ([source](https://docs.koog.ai/prompts/index.md)) - [Agent-Specific Query Routing](https://awesome-repositories.com/f/data-databases/semantic-query-routing/agent-specific-query-routing.md) — Directs user inputs to specific tools or sub-agents using semantic intent and graph-based routing patterns. ([source](https://docs.koog.ai/examples/index.md)) - [State Checkpointing](https://awesome-repositories.com/f/data-databases/state-checkpointing.md) — Saves and restores full execution state and conversation history to enable session recovery and rollbacks. - [Type-Safe State Stores](https://awesome-repositories.com/f/data-databases/type-safe-data-abstractions/type-safe-state-stores.md) — Passes information using a type-safe key-value system to maintain data integrity across different nodes or subgraphs. ([source](https://docs.koog.ai/data-transfer-between-nodes/index.md)) ### Networking & Communication - [MCP Transport Protocol Supports](https://awesome-repositories.com/f/networking-communication/network-transport-protocols/multi-protocol-transport-abstraction/mcp-transport-protocol-supports.md) — Supports multiple communication methods for client interaction, including JSON-RPC over HTTP and SSE. ([source](https://docs.koog.ai/a2a/a2a-server/index.md)) - [Structured Object Streaming](https://awesome-repositories.com/f/networking-communication/response-streaming-utilities/partial-response-streams/structured-object-streaming.md) — Performs incremental parsing of structured data objects as they are streamed from the model. ([source](https://docs.koog.ai/streaming-api/index.md)) ### System Administration & Monitoring - [OpenTelemetry-Integrated Monitors](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/real-time-process-monitors/agent-interaction-monitors/opentelemetry-integrated-monitors.md) — Integrates OpenTelemetry to capture agent lifecycle events and model interactions as spans for external tracing. - [GenAI Execution Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/workflow-performance-diagnostics/genai-execution-monitoring.md) — Tracks GenAI-specific metrics such as token usage and tool call counts using standard conventions. ([source](https://docs.koog.ai/features/open-telemetry/index.md))