Loading...
Loading...
Judgeval: The Continuous-Improvement Stack for Agents. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Judgeval. This is an automatic list. We have not written a researched verdict for Judgeval yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Ridiculous speed. Readable code.
B4.run is an open source TypeScript framework for building AI agents in which files are features. A single command scaffolds a new project, and each agent is simply a folder: an index file picks the model and writes the system prompt, and every TypeScript file placed in its tools folder becomes one of the agent's tools...
Instant recall for coding agents.
ctx is an open source command line toolchain for context engineering with coding agents. Its core job is to make the session history that agents such as Claude Code, Codex, Cursor, OpenCode, Gemini CLI and Copilot CLI already leave on your machine searchable, so a new session can recover earlier decisions, failed appro...
Agent framework for the JVM.
Embabel is an agentic AI framework for the Java Virtual Machine. It is written in Kotlin with a usage model intended to feel natural from Java, and its argument is that the qualities which matter once AI becomes mission critical, namely context handling, reliability, type safety, performance, observability and integrat...
Grix : Work with agents like talking to people.
Grix is a messaging style app for working with AI coding agents from a phone or a computer. It turns agents such as DeepSeek Harness, Codex, Claude, Kimi, Qwen, OpenCode, GitHub Copilot and Cursor into contacts, so a developer can message them, invite them into group chats and @mention them with tasks, then follow prog...
The Juggler Code Agent
Juggler is a GUI first AI coding harness built by Julian Storer, the developer behind JUCE, Tracktion and Cmajor. It is a desktop interface and matching server for working with coding agents over long sessions, with every model transaction open to inspection. The backend is a native Go server, and the interface is typ...
A persistent workspace for development work that self-improves and continues beyond one session.
KiroCrew, written Kiro Crew by the vendor, is a persistent, open source development workspace from the team behind the Kiro IDE. It is built around agents that keep memory, lessons and skills between sessions so that work resumes instead of restarting. Corrections are turned into lasting lessons, and repeated workflow...