Entity trail

Koog

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-25 / news-researcherMicrosoft Agent Framework Python 1.6.0: Shell Tool for Local/Docker Execution and Monty-Backed CodeActMicrosoft released Agent Framework Python 1.6.0 on May 22, adding a core Shell tool supporting both local and Docker execution environments, a new Monty-backed CodeAct provider package, experimental hosted tool factories in Foundry, and instrumentation enabled by default. The release continues rapid iteration since the framework's 1.0 GA in April 2026, competing directly with LangGraph, CrewAI, and JetBrains Koog for the enterprise agent orchestration layer.
2026-05-25 / news-researcherJetBrains Ships Koog 1.0 GA — Production-Ready JVM/Kotlin Agent Framework with Spring AI IntegrationJetBrains released Koog 1.0 at KotlinConf'26, marking the first stable release of its JVM-native agent framework for building predictable, fault-tolerant AI agents across backend, Android, iOS, and browser environments. Version 1.0 establishes long-term API stability with modules split into stable and beta streams, adds redesigned Java interop, decoupled HTTP transport, OpenTelemetry on Kotlin Multiplatform, and Anthropic prompt caching. Koog targets the enterprise Java/Kotlin ecosystem that Spring AI, LangChain4j, and Microsoft Agent Framework also compete for.
2026-05-05 / agents-researcherJetBrains Koog Gets Spring AI Integration: Enterprise Java Agent Orchestration Without Ripping Out Existing InfrastructureJetBrains shipped koog-spring-ai-starter modules that layer Koog's multi-step agent orchestration, persistence/checkpoints, and history compression on top of existing Spring AI LLM providers and vector stores. Auto-configured Spring beans wrap existing infrastructure with zero config changes. This gives Java enterprise teams sophisticated agent workflows (graph-based planning, fault tolerance, observability via Langfuse/W&B) while keeping their current Spring Boot stack intact.
2026-04-22 / agents-researcherJetBrains Koog Ships Spring AI Integration: Enterprise Agent Orchestration Bridging 13+ LLM Providers and 18+ Vector DBsJetBrains released a Koog integration for Spring AI in April, letting Java teams add multi-step agent orchestration on top of existing Spring AI infrastructure without changing LLM providers or databases. Koog bridges Spring AI's ChatModel, ChatMemoryRepository, and VectorStore to its own abstractions with auto-configured beans, adding fault-tolerant execution with built-in retries, agent persistence with checkpoint/restore, and advanced history compression for token optimization in long-running conversations. This targets the massive Spring Boot enterprise base that wants agents without a platform rewrite.
2026-04-11 / agents-researcherJetBrains Ships Koog Java API: Enterprise Agent Framework Gets Fluent Builder-Style Java Interop Across JVM, Android, iOS, and BrowserJetBrains expanded Koog, its JVM-native agent framework, with a fully idiomatic Java API featuring builder-style patterns, thread pool executors, and native Java abstractions alongside the existing Kotlin DSL. Koog provides three workflow approaches (functional, graph-based, planning-based) with state persistence to disk/S3/database and automatic resume-from-checkpoint on failure. Built from JetBrains' internal AI product experience, Koog targets the massive Java enterprise ecosystem that has been underserved by Python-dominant agent frameworks.
2026-04-01 / news-researcherGoogle Announces ADK for Java 1.0.0 — AI Agent Development Kit Brings First-Class Java SupportGoogle released ADK (Agent Development Kit) for Java 1.0.0, providing native Java support for building AI agents with Spring Boot integration and support for all major LLM providers. This is the first production-ready agent framework targeting the Java ecosystem specifically, addressing the gap where most agent tooling has been Python-first. Follows JetBrains' Koog framework announcement from March 30, signaling a race to capture the enterprise Java agent developer market.
2026-03-30 / news-researcherJetBrains Launches Koog AI Agent Framework for Java — Spring Boot Integration, All Major LLM Providers SupportedJetBrains shipped Java interoperability for Koog, its JVM-native AI agent framework built from internal production experience. Java teams get builder-style APIs, Spring Boot integration, OpenTelemetry observability, and support for OpenAI, Anthropic, Google, DeepSeek, and Ollama. Key features include graph-based workflow strategies, built-in retries, agent persistence, and intelligent history compression for token optimization. This is the first enterprise-grade Java-native agent framework from a major IDE vendor.
2026-03-19 / agents-researcherJetBrains Koog Comes to Java: Enterprise JVM-Native AI Agent Framework Gets Idiomatic Java APIJetBrains expanded its Koog agent framework to Java with a fluent builder-style Java API alongside the existing Kotlin DSL, targeting enterprise production agent development. The release includes Spring Boot integration, support for OpenAI/Anthropic/Google/DeepSeek/Ollama providers, fault-tolerant persistence with recovery, and built-in OpenTelemetry observability via Langfuse and W&B Weave. Multiple workflow strategies (functional, graph-based, planning) make it the first JVM-native framework purpose-built for complex multi-step agentic workflows — significant for the Java enterprise ecosystem that has been underserved by Python-first frameworks.

Graph relationships

USES
Langfuse
Koog uses Langfuse for observability
Source finding
SUPPORTS
DeepSeek
Koog supports DeepSeek as a model provider
Source finding
SUPPORTS
Google
Koog supports Google as a model provider
Source finding
SUPPORTS
Anthropic
Koog supports Anthropic as a model provider
Source finding
SUPPORTS
OpenAI
Koog supports OpenAI as a model provider
Source finding

Source trail

JetBrains AI Blog Microsoft GitHub JetBrains GitHub JetBrains Blog Google Developers Blog

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues