A NetBeans plugin that lets AI agents compile, load, and execute LLM-generated Java code directly on the IDE's JVM. Each agent gets its own ClassLoader to manage bytecode at runtime and can communicate with other agents via Java objects. It targets Java developers and AI tooling builders who want agents that produce runnable code immediately inside the IDE.
Agent-run is a tool that lets you run a coding agent (an LLM-powered agent that writes code) inside a sandboxed environment. It solves the problem of safely executing AI-generated code without risking system integrity, targeting developers who want to experiment with or deploy coding agents.
Agent-run is a tool that lets you run a coding agent (an LLM-powered agent that writes code) inside a sandboxed environment. It solves the problem of safely executing AI-generated code without risking system integrity, targeting developers who want to experiment with or deploy coding agents.
CleanSlate is an IDE that integrates an agent manager directly, allowing developers to create, manage, and switch between multiple coding agents without leaving the editor. It solves the friction of toggling between separate agent management tools and the IDE, enabling seamless context preservation and multi-agent orchestration for developers working with LLM-powered coding agents.
CleanSlate is an IDE that integrates an agent manager directly, allowing developers to create, manage, and switch between multiple coding agents without leaving the editor. It solves the friction of toggling between separate agent management tools and the IDE, enabling seamless context preservation and multi-agent orchestration for developers working with LLM-powered coding agents.
A fork of ThinkRail, JetBrains' open-source IDE shell for AI coding agents, which is hardwired to a single agent. The fork adds a prototype plugin API so multiple agents can run in the same worktree-per-tab UI, starting with Claude Code integrated as a builtin plugin. It targets developers who want choice of coding agent inside one IDE shell.
A fork of ThinkRail, JetBrains' open-source IDE shell for AI coding agents, which is hardwired to a single agent. The fork adds a prototype plugin API so multiple agents can run in the same worktree-per-tab UI, starting with Claude Code integrated as a builtin plugin. It targets developers who want choice of coding agent inside one IDE shell.
Zeroparams is an art project that replaces an LLM in an OpenAI-compatible coding agent with a human. A custom VSCode extension intercepts completion requests and sends them to a chat window, where the human can edit files and run CLI commands via tool calls. It explores the interface between programmers and models, with real subscriptions.
Zeroparams is an art project that replaces an LLM in an OpenAI-compatible coding agent with a human. A custom VSCode extension intercepts completion requests and sends them to a chat window, where the human can edit files and run CLI commands via tool calls. It explores the interface between programmers and models, with real subscriptions.
A developer asks how to build AI agents in non-Python languages, noting that while most powerful frameworks (LangChain, LangGraph, Pydantic AI) are Python-centric, alternatives are emerging: LangChain/LangGraph have TypeScript packages, Spring AI for Java, and Microsoft Agent Framework for C#. The discussion highlights the growing ecosystem for agent development outside Python.
A developer asks how to build AI agents in non-Python languages, noting that while most powerful frameworks (LangChain, LangGraph, Pydantic AI) are Python-centric, alternatives are emerging: LangChain/LangGraph have TypeScript packages, Spring AI for Java, and Microsoft Agent Framework for C#. The discussion highlights the growing ecosystem for agent development outside Python.