Loading...
Loading...
Crit: Your feedback loop with the agent. 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 Crit. This is an automatic list. We have not written a researched verdict for Crit 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.
Slack CLI for humans and AI agents.
SlackCLI is a command line tool for reading, sending, searching and replying across one or many Slack workspaces from the terminal. It is distributed as a single binary for macOS, Linux and Windows with no runtime to install. Its distinguishing choice is how it signs in. Rather than requiring a registered Slack app, O...
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...
A lightweight cli for running single-purpose AI agents.
Axe is an open source command line tool that runs LLM powered agents the way Unix runs programs. Each agent does one focused job, is defined in a TOML file with its own system prompt, model, skill files, context files, working directory and persistent memory, and is run from the terminal. Data is piped in and results c...
Live messaging for coding agents
Concord is an open source MCP server that gives coding agents a shared work state so they can coordinate before their changes collide. Installed from npm and run locally against a repository, it lets agents such as Claude Code, Codex and Cursor see who is working on what, reserve the files or scope they intend to edit,...
Catch intent conflicts before code conflicts.
Foremerge is an open source coordination protocol for coding agents, layered on top of Git. It exists to solve a specific failure mode: when several agents work on one repository from separate worktrees, Git compares text, so two edits that are each sensible on their own can land in different files, merge without compl...
30 sec to give your AI agents persistent memory.
GrayMatter is a persistent memory layer for AI coding agents. Agents are stateless by default, so each run feeds the whole conversation history back in and the token cost grows with it. GrayMatter stores facts locally, recalls them by meaning and injects only the handful that matter to the task at hand. It is built fo...