Off the Bit
Tools: Claude Code
Category: AI assistants and agents
Site: claude.ai
Claude Code
Anthropic's agentic coding tool. Runs in the terminal with access to the repository, the shell and the test suite.
An agent that can run the tests it just broke.
What it is sold for
Working on a codebase from the terminal with tools rather than suggestions.
Named alongside
These entries mention each other by name. It is a weak relationship and it is the only one the catalogue can show without inventing something.
Named by:
- Runs coding agents inside hardware-isolated microVMs, so an agent with shell access cannot reach the host.
- An open autonomous agent that scans a stack, generates specifications through interviews, and works from them.
- Turns tickets into working code, with agents picking up issues rather than being prompted.
- Assigns work to a group of agents and tracks it, treating them as a team roster rather than as one assistant.
- A virtual pet that lives in the Claude Code status line and reacts to what you are doing.
- Runs coding agents as long-lived workers with objectives and memory, so a session survives being interrupted.
- Asks questions about an idea, then builds and hosts the application including accounts, payments and a domain.
- A local-first knowledge graph and retrieval store for agent memory, built on a published pattern.
- Anthropic's model family, and the one this catalogue's own tooling is written against.
- Captures every assistant conversation from Cursor, Copilot, Claude Code and Codex, stored locally.
- Open-source marketing and search skills packaged for agents to load and use.
- Parsed local agent session logs to find where the money went. The repository returns 404.
- An agent skill for deploying to Kubernetes, portable across any assistant that reads a skill file.
Same shelf
The rest of ai assistants and agents, alphabetically. Sharing a category is a filing decision, not a relationship.
- Generates and hosts WordPress sites, with the build and the hosting sold as one product.
- Agent Shadow Brain did not answerListed as a background analysis agent. The repository returns 404.
- A TypeScript toolkit that puts one interface in front of many model providers, including streaming and tool calls.
- An agent that spends more compute at inference time on harder engineering problems rather than answering immediately.
- Pair programming in the terminal. Reads the repository, proposes edits, and commits them to git with a message.
- Amazon's original completion assistant. The name is retired and the address now serves Amazon Q Developer.
- Amazon's coding assistant, integrated with AWS accounts and services rather than with the editor alone.
- Sourcegraph's agent and development environment, including unsupervised runs in hosted sandboxes.
ImranTools[Claude Code]