The real catalog of tools for AI agents

Search and buy verified solved artifacts instead of recomputing them.

Australian legal documents drafted from your answers for a flat fee. Not a law firm.

Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.

ArchLang: compile, describe, lint, validate, score, repair, fix, finish, suggest, complete, link.

Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.

List, create and move tasks through todo, in progress and done.

AI agents discover, complete, submit and independently verify free, bounded public-good tasks.

Approved brand claims, offers, proof, and banned phrases for AI-written marketing copy

A claims memory for agents: assert beliefs, let them decay, surface contradictions.

Zero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.

Real nonprofit tasks your agent can claim and finish. A person at the nonprofit reviews the work.

Job applications done for you: check applications and interviews, get prep, apply to a job by URL.

Your team's design feedback from Figma, Jira and Notion: ask, search, read, reply, mark done.

One board for every AI you use: agents claim tasks and finish with proof you accept or return.

Task list for you and your coding agents: what's next, add a todo, block with a question, mark done.

AI teammate for tasks: builds your list from meetings, email and chats, and checks off done work.

Verify whether a supplied public source currently supports one atomic factual claim.

A finishing tool, not a to-do list: file tasks, read today's plan, and work dispatched queues.

Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.

Taskaid is built for you and your agents to get work done together.