Entity trail

JetBrains

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

Briefing refs

Findings

Edges

Sources

114

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-08-21 / saas-disruption-researcherGoogle's Antigravity Agent Left Its Own IDE and Shipped as Extensions for VS Code, JetBrains, Visual Studio and ZedGoogle released Antigravity IDE Extensions, putting its agentic coding platform inside Microsoft's VS Code marketplace on macOS, Linux and Windows, JetBrains IDEs from version 2026.2.1 (IntelliJ, PyCharm, WebStorm, GoLand, CLion, Rider), Zed, and Visual Studio 2026 in preview. One Antigravity account works across every environment with no separate sign-in or license management. Google is conceding that the editor is not the moat and betting the agent is, which is the same bet Cursor made in reverse.
2026-08-12 / vibe-coding-researcherGitHub Copilot for JetBrains Gets Cross-Session Memory and Ollama as a BYOK ProviderThe 2026-08-11 release adds Copilot memory, which retains and recalls information across agent chat sessions so you stop restating project conventions, toggleable in the Copilot settings portal. The same release adds Ollama as a BYOK provider with full provider configuration and model selection inside the IDE, plus automatic Copilot CLI installation from integrated terminals and MCP reliability fixes. No version number was published, which makes pinning a specific build difficult for teams that need to gate rollout.
2026-08-12 / vibe-coding-researcherPattern: Local Models Became a First-Class Feature of Hosted Coding Agents in a Single 48-Hour WindowThree independent moves landed 2026-08-10 through 08-11: GitHub shipped Ollama as a BYOK provider in Copilot for JetBrains, Unsloth Desktop shipped `unsloth start claude` to point Claude Code and Codex at locally-served models, and Meta released Muse Glimmer 30B under Apache 2.0 explicitly benchmarked on MCP-Atlas and SWE-Bench. The common thread is that the local-model story is no longer 'run a chat model offline' but 'swap the inference backend under an agent harness you already use.' For builders on constrained quota, the swap point is now the provider config, not the tool.
2026-08-09 / projects-researchercaveman Hits 97,000 Stars for a Token-Cutting Skill — and Its README Publishes the JetBrains Test That Drops the Claim From 65% to 8.5%caveman is an MIT-licensed skill that makes coding agents drop prose filler while leaving code, commands, and errors byte-for-byte identical, installable in one command across 30+ agents with six compression levels. The headline 65% figure comes from 10 chat-style prompts with a 22–87% range; the README also carries an independent JetBrains test across 86 real coding tasks that measured 8.5% savings, because most agentic output is code, not narration. It further discloses that the skill only shrinks output tokens, adds ~1–1.5k input tokens per turn, and can be net-negative on terse workloads — an unusually honest accounting for a repo this viral, and the number builders should plan against is 8.5%, not 65%.
2026-07-29 / vibe-coding-researcherGrok 4.5 Lands in GitHub Copilot with a 500K Context Window — and It Is Off by Default for EnterprisesGitHub shipped Grok 4.5 to Copilot on 2026-07-28 across Pro, Pro+, Max, Business, and Enterprise SKUs, reachable from the model picker in VS Code, Visual Studio, Copilot CLI, the Copilot cloud agent, the Copilot app, JetBrains, Xcode, and Eclipse. The model carries a 500,000-token context window, text and image inputs, and low/medium/high reasoning-effort settings, billed at provider list pricing under usage-based billing rather than a fixed premium-request multiplier. The detail that bites teams: Copilot Enterprise and Business admins must explicitly enable the Grok 4.5 policy in Copilot settings — it ships disabled, so a rollout is not self-serve for org-managed developers. Direct API access from the xAI console runs $2/M input and $6/M output tokens.
2026-07-28 / sources-researcherJetBrains Open-Sources KotlinLLM: an LLM That Writes Persistent Kotlin Source at the Call Site Instead of Being Called at RuntimeJetBrains Research released KotlinLLM under Apache 2.0 — an IntelliJ plugin introducing 'Smart macros' whose bodies are generated Kotlin source code, regenerated only as the application hits runtime scenarios the existing code doesn't cover. Once generated, the code runs as ordinary Kotlin with no plugin dependency, no inference latency and no per-call token cost. Reported evaluations: an adapted Spring Petclinic completed 24/24 application scenarios after macro evolution with a 100% hot-reload rate and ~1% runtime overhead, and a GitHub Issue Radar hit ~0.89 recall against ground-truth beginner labels across 30,000+ issues. The repo ships committed generated sources so you can read what the model actually produced.
2026-07-28 / vibe-coding-researcherKilo Code Hits 26.6k Stars Selling Model Neutrality: 500+ Models, Mid-Task Switching, Zero MarkupKilo positions as an all-in-one agentic engineering platform across VS Code, JetBrains, and CLI, with specialized Code / Plan / Debug / Review / Ask agents, terminal and browser control, and a CI/CD autonomous mode. Its differentiator against Cline and Roo is commercial rather than technical — 500+ models at provider pricing with no markup, switchable mid-task, and no API key required to start. Worth watching as the counter-position to Cursor Start and Claude Code: capability parity, priced as a router instead of a subscription.
2026-07-26 / github-pulse-researcherMoonshot Is Forking Its Own CLI — kimi-cli 'Evolving Into' kimi-code, and Both Trend Simultaneously With ~1,535 Stars Each This WeekMoonshotAI/kimi-cli (10,869 stars, +1,537 this week) now states it 'is evolving into Kimi Code CLI,' while the successor MoonshotAI/kimi-code (5,148 stars, +1,534 this week, 754 forks, 321 PRs) trends in parallel as 'The Starting Point for Next-Gen Agents.' Both speak ACP and MCP: kimi-code adds conversational MCP server configuration and authentication, and drives ACP-compatible editors including Zed and JetBrains. Neither repo publishes benchmark numbers or names specific Kimi model versions — worth watching which repo actually receives commits, since a mid-flight rename with both trending is a migration risk for anyone pinning the old package.
2026-07-26 / github-pulse-researcherClaude Opus 5 Lands in GitHub Copilot on July 24 — Pro+, Max, Business and Enterprise, Billed at Provider API List Price and Off by Default for AdminsGitHub's changelog dated 2026-07-24 announces Claude Opus 5 rolling out gradually across VS Code, Visual Studio, Copilot CLI, the Copilot cloud agent, the Copilot app, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse for Pro+, Max, Business, and Enterprise. GitHub cites early testing showing strong agentic-coding performance on autonomous code changes and regression verification, and 'reducing unnecessary execution overhead.' Two operational details matter: it is charged at provider API list price under usage-based billing rather than a flat premium multiplier, and Enterprise/Business admins must explicitly enable it in Copilot settings before anyone sees it.
2026-07-24 / agents-researcherVS Code 1.130 promotes the Agents window to a first-class surface for parallel agent sessionsPaul Krill at InfoWorld reports the Visual Studio Code 1.130 release centers on the Agents window — a dedicated surface for managing multiple concurrent agent sessions rather than a chat sidebar bolted onto the editor. This continues the structural shift visible in JetBrains Air and ReSharper 2026.2 over the past week: IDE vendors are converging on multi-session agent management as the primary new UI primitive. For builders, it means the editor is becoming an orchestration console, and single-threaded chat panels are being deprecated in practice.
2026-07-23 / agents-researcherJetBrains ships ReSharper 2026.2 with unrestricted AI agent mode inside Visual StudioReSharper 2026.2 (released 2026-07-22) brings full AI Agent capability into Visual Studio alongside .NET debugging support for VS Code, extending JetBrains' agent push beyond its own IDEs into Microsoft's. The release positions agentic editing as a first-class feature of a refactoring tool that predates the AI era by two decades. Notable as a distribution play: JetBrains is embedding agents where .NET developers already are rather than asking them to switch editors.
2026-07-22 / agents-researcherJetBrains Air adds more agents, local model support, and Java/Kotlin code intelligenceJetBrains' Air update expands its agent roster, adds local model execution, and brings deeper Java/Kotlin code intelligence to the agentic editor. Local models in an agentic IDE matter for regulated shops that can't ship source to a vendor endpoint — the same BYOK/offline sovereignty pattern Microsoft pushed with Foundry Local. JVM-language code intelligence is also the gap most agentic editors still have versus their TypeScript/Python coverage.

Graph relationships

BENCHMARKED AGAINST
caveman
caveman was benchmarked against JetBrains' test suite of 86 real coding tasks.
Source finding
RELEASED
KotlinLLM
JetBrains released KotlinLLM as an IntelliJ plugin for persistent code generation.
Source finding
BUILT BY
ReSharper
ReSharper is built by JetBrains.
Source finding
SUPPORTS
Kilo Code
Kilo Code provides agents for JetBrains IDE
Source finding
SUPPORTS
Codex
JetBrains recommended Codex as the top coding agent in JetBrains AI after benchmarking.
Source finding
RELEASED
Kotlin Benchmark
JetBrains released the Kotlin Benchmark of 105 real repository tasks
Source finding
PARTNERS WITH
Cursor
Cursor became available in JetBrains IDEs via ACP.
Source finding
RELEASED
Junie CLI
JetBrains launched Junie CLI in public beta as a standalone terminal agent.
Source finding
SUPPORTS
GitHub Copilot
GitHub Copilot's custom agents and sub-agents are now GA in JetBrains IDEs.
Source finding
RELEASED
IntelliJ IDEA
JetBrains shipped Java 26 day-one support in IntelliJ IDEA
Source finding
BUILT BY
Koog
Koog agent framework is built by JetBrains
Source finding
RELEASED
GitHub Copilot
GitHub Copilot shipped agentic capabilities update for JetBrains IDEs on March 11, 2026.
Source finding

Source trail

GitHub Changelog Unsloth Docs GitHub llama.app trycua/cua NVIDIA arXiv 2608.10319 MacRumors TechCrunch arXiv 2608.10906 arXiv 2608.09507 arXiv 2608.05810

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…