1,400 tools found
A Jupyter notebook where an AI agent requests paid API data through application-controlled spending limits and Amazon Bedrock AgentCore Payments.
cursor-bridge is a Rust binary that runs Claude Code CLI using your Cursor subscription backend through automatic proxy management.
Staff-engineer control layer for AI coding agents: routes only the architectural constraints relevant to the file being edited, then requires verification.
claude-thermos keeps Claude Code's prompt cache warm while a subagent runs long, avoiding the expensive full re-encode when the main agent resumes.
capn-hook is persistent memory for coding agents - it saves which files answer a question, so the next session skips re-exploring the codebase.
aict reimplements 33 Unix coreutils with structured XML/JSON output so AI agents never have to parse plaintext column formats.
Grepathy extracts undocumented decisions from Claude Code session transcripts into a committed markdown why-file, so PR reviewers can see the reasoning.
Step-by-step guide turning a Big Mouth Billy Bass toy into a real-time voice assistant on a Raspberry Pi 5, via Strands Agents and Amazon Nova Sonic.
Runs a coding agent inside a disposable Linux VM instead of your machine - full root, no permission prompts, network allow-listed, one command.
mindwalk replays Claude Code and Codex coding-agent sessions as glowing light moving across a 3D map of your codebase, fully local.
docx-cli lets AI agents edit, redline, and comment on Word documents via stable locators and plain commands, without touching or corrupting the XML.
LoopGain is an open-source cost controller that stops AI agent loops the moment they converge, instead of running to a fixed max_iterations cap.
