Rocky Tested homeRocky Tested

Reviews

No verdicts published yet. Here is what is in the lab right now.

Rocky in his lab coat and goggles
Rocky dressed for Coding agents
Coding agents shootout

Claude Code token-saver shootout

Four add-ons that try to make AI coding agents like Claude Code waste fewer tokens. claude-mem saves and re-injects memory between sessions, context-mode shrinks tool output, Caveman makes the agent answer in fewer words, and XERJ swaps grep-style searching for an index.

Repo⭐ Stars🍴 ForksOpen issuesLast pushLanguage
claude-mem101.4k8.9k121TypeScript
context-mode30.5k2.2k356TypeScript
Caveman113.3k6.6k51Go
XERJ7.7k40525Rust

License: Apache-2.0, NOASSERTION

Live from GitHub, fetched

⏱️ ETA: Not scheduled yet (estimates appear here once Rocky plans the run)

TESTING…  Details →

Rocky dressed for AI models
Local models & inference review

AirLLM

A Python library for running very large language models on a small GPU. Its README says 70B models fit on a single 4 GB card without quantization, by streaming the model a layer at a time.

Repo⭐ Stars🍴 ForksOpen issuesLast pushLanguage
AirLLM39.2k4k167Jupyter Notebook

License: Apache-2.0

Live from GitHub, fetched

⏱️ ETA: Not scheduled yet (estimates appear here once Rocky plans the run)

TESTING…  Details →

Rocky dressed for Security
Coding agents review

REA (reverse engineer anything)

An MCP server that lets an AI agent take apart an app it doesn't have the source for (native binaries, Electron and JavaScript apps, .NET, websites) and explain how a feature works, with the evidence behind each answer.

Repo⭐ Stars🍴 ForksOpen issuesLast pushLanguage
REA306.2k77.5k1.2kTypeScript

License: MIT

Live from GitHub, fetched

⏱️ ETA: Not scheduled yet (estimates appear here once Rocky plans the run)

TESTING…  Details →

Rocky dressed for Robotics
Agent frameworks & team kits shootout

Parallel AI coding agents shootout

Tools that run several AI coding agents at the same time, each on its own task or git worktree, and then let you review all the changes in one place. Orca, Kandev and OpenHands are workspaces for this; Ruflo is a multi-agent harness; Hermes Agent is a self-improving agent.

Repo⭐ Stars🍴 ForksOpen issuesLast pushLanguage
Orca95.3k6.1k8.5kTypeScript
Ruflo76k9k1kTypeScript
OpenHands91.1k12.1k1kTypeScript
Hermes Agent254.7k55.4k49.7kPython
Kandev964157138Go

License: AGPL-3.0, MIT

Live from GitHub, fetched

⏱️ ETA: Not scheduled yet (estimates appear here once Rocky plans the run)

TESTING…  Details →

Rocky dressed for CAD
CAD & 3D review

SolidCraft

An open-source parametric 3D CAD app written in Rust that runs on the desktop or in the browser. It has a built-in MCP server so AI agents can sketch, extrude and edit models.

Repo⭐ Stars🍴 ForksOpen issuesLast pushLanguage
SolidCraft4.1k471648Rust

License: Apache-2.0

Live from GitHub, fetched

⏱️ ETA: Not scheduled yet (estimates appear here once Rocky plans the run)

TESTING…  Details →