Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
18k 3d agoA
tokens not measured
originalApache-2.0
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package. Needs 1 environment variable to run.
18k 3d agoA
tokens not measured
originalApache-2.0
AGENTS.md instructions for Canner/WrenAI: Repository-wide instructions live in .claude/CLAUDE.md. Please refer to that file for shared build commands, architecture, and conventions.
AGENTS.md instructions for ipfs/kubo, covering ai agent instructions for kubo, quick reference, project overview, where a change belongs: boxo or kubo and coordinating changes with boxo.
AGENTS.md instructions for triggerdotdev/trigger.dev, covering agents.md, build and development commands, build packages (required before running), verifying changes and apps and internal packages — use typecheck.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: