Loading...
Loading...
Inspect: Entity-level code review. 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 Inspect. This is an automatic list. We have not written a researched verdict for Inspect 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.
Your feedback loop with the agent
Crit is a local review tool for the output of AI coding agents. Instead of scrolling through terminal diffs after an agent has touched a dozen files, you open the changes in a browser, click a specific line, type what is wrong, and hand the comments back to the agent. When the agent edits the work, Crit reloads with a ...
A workflow harness that helps AI coding agents plan, review, test, and ship safer code.
Nanostack is a set of skills that adds a team style review process to AI coding agents, aimed at people building software with AI who are not engineers. The agent still writes the code, and Nanostack runs the checks a real team would, then reports each result in plain words. The default sprint runs through a series of...
A Herdr client for any screen.
Roamgate is an open source browser client for Herdr, a server that keeps coding agents running in real terminal sessions. It brings those terminals, conversations and code changes into one browser workspace that works on desktop or phone, so a developer can check on agents away from their main machine. It was formerly ...
docx ↔ LLM translator.
Adeu is a set of legal AI tools that work inside the software legal teams already use, together with an open source redlining engine for developers. For teams, it turns messy legal email threads into a brief with a draft reply, reviews contracts against the company's playbook, and returns the original Word document wit...
The fastest developer workflow for every AI coding agent.
Agent Manager is a terminal user interface, written in Go and running on top of tmux, that lets a developer run many AI coding agents side by side and control them from a single list. Each row is a real tmux session running the developer's own installed command line agent, with its existing login, configuration and MCP...
One person, one software company.
AgentHub is an open source Electron desktop app that organises Claude Code agents into a virtual software company run by one person. It ships with 47 specialised agent roles across nine departments, including product, engineering, design, marketing, QA, project management and operations, and manages their sprints, task...