Every AI agent, one table
TODO for AI is a TODO list where the items get done by AI agents. It logs into your tools, does the work and shows you the result. It reads your business first, so over time it proposes the TODOs instead of only closing them. Here is how that compares, cell by cell.
LinearShared board. Yes: Yes, issuesOpen-ended work. Partly: Workspace, MCP and reposShell you own. Partly: Linear's sandboxYour browser. Partly: Sandbox browser, for testingModel choice. Yes: Claude, GPT, GLM, per workspaceProposes the work. Partly: Triage suggestions, Loops
NotionShared board. Yes: Yes, agents shareableOpen-ended work. Partly: Workspace and MCP appsShell you own. No: NoYour browser. Partly: Its own browsingModel choice. Yes: Claude, GPT, Gemini, GrokProposes the work. Partly: Runs on your triggers
ClickUpShared board. Yes: Yes, assignableOpen-ended work. Partly: Workspace and skillsShell you own. No: NoYour browser. No: NoModel choice. Yes: Max, Claude, GPT, GeminiProposes the work. Partly: Ambient, on your rules
AsanaShared board. Yes: Yes, AI teammatesOpen-ended work. Partly: Workspace and connected appsShell you own. No: NoYour browser. No: NoModel choice. Partly: AI Studio rules onlyProposes the work. Partly: Suggests a teammate per project
LindyShared board. Partly: Per user, shared poolOpen-ended work. No: Build the flow firstShell you own. No: NoYour browser. No: NoModel choice. Yes: Per nodeProposes the work. Partly: Runs on your triggers
Claude CoworkShared board. Partly: Projects shareable on TeamOpen-ended work. Yes: YesShell you own. Partly: Their sandbox, your foldersYour browser. Yes: Claude in ChromeModel choice. No: Anthropic onlyProposes the work. No: No
Copilot CoworkShared board. No: No shared task boardOpen-ended work. Partly: Microsoft 365 appsShell you own. No: Microsoft cloudYour browser. Partly: Local Edge, previewModel choice. Partly: Picker in Frontier previewProposes the work. No: No
Claude CodeShared board. No: Private sessionOpen-ended work. Partly: Repo first, MCP beyondShell you own. Yes: YesYour browser. Yes: Claude in ChromeModel choice. No: Anthropic onlyProposes the work. No: No
OpenAI CodexShared board. No: Private task listOpen-ended work. Partly: Repo shapedShell you own. Yes: YesYour browser. No: NoModel choice. No: OpenAI onlyProposes the work. No: No
CursorShared board. No: Private, repo configOpen-ended work. Partly: Repo shapedShell you own. Yes: YesYour browser. Partly: To check your appModel choice. Yes: Multi-vendor, meteredProposes the work. No: No
GitHub CopilotShared board. Yes: Yes, GitHub issuesOpen-ended work. Partly: Repo shapedShell you own. Yes: CLI local, cloud on runnersYour browser. No: NoModel choice. Yes: OpenAI, Anthropic, Google, xAIProposes the work. No: No
ChatGPTShared board. No: Private chatsOpen-ended work. Yes: YesShell you own. Partly: Their sandboxYour browser. Partly: Its own, plus connectorsModel choice. No: OpenAI onlyProposes the work. Partly: Suggests from memory
ManusShared board. No: Tasks shared one by oneOpen-ended work. Yes: YesShell you own. Partly: Their cloud; local folders via desktop appYour browser. Yes: Browser Operator extensionModel choice. Partly: Vendor picks, or BYOK via FlexProposes the work. No: No
OpenClawShared board. No: Chat threadsOpen-ended work. Yes: YesShell you own. Yes: The box you hostYour browser. Yes: CDP, self-configuredModel choice. Yes: Any, BYOKProposes the work. Partly: Heartbeat alerts
Hermes AgentShared board. No: Chat threadsOpen-ended work. Yes: YesShell you own. Yes: The box you hostYour browser. Yes: CDP, self-configuredModel choice. Yes: Any, BYOKProposes the work. Partly: Cron you write
TODO for AIShared board. Yes: Yes, one boardOpen-ended work. Yes: YesShell you own. Yes: Your PC + cloud VMYour browser. Yes: Your Chrome profileModel choice. Yes: Any provider, per agentProposes the work. Yes: From your site, learns from dismissalsTwo groups are converging on the same product. Linear, Notion, ClickUp and Asana had the shared board and added agents, which act inside the app and never get a command line. Claude Code, Cowork, Codex, Cursor, OpenClaw and Hermes had the command line and added task lists, which stay private to one person. GitHub is the closest to both, and only accepts work that can become a pull request.
None of them starts the work. Every row except ours runs on a prompt, a trigger or a rule somebody wrote. That is fine for work you already know about. Most of what slips is work nobody thought to write down.
Each comparison in full
Claude CodeAnthropic's coding agent, tied to Claude models and Claude subscription tiers.
OpenAI CodexOpenAI's coding agent: an open-source CLI plus a cloud sandbox inside ChatGPT.
CursorA VS Code fork with built-in AI chat, unlimited tab completion and repo-scoped cloud agents.
OpenCodeOpen-source terminal coding agent, bring your own keys, any provider.
ClineOpen-source VS Code agent extension, bring your own keys, plan and act modes.
AiderThe original open-source pair-programming CLI, git-native, any model.
OpenHandsOpen-source autonomous software agent with a self-hosted or cloud workspace.
Claude CoworkAnthropic's agent, merged into Claude itself in September 2026: ask for anything and Claude decides whether it is an answer or a task it works through on its own.
ChatGPTThe default AI assistant, with agent mode, deep research and connectors bolted onto the chat product.
LindyNo-code AI teammates for business workflows: email, CRM, meetings and support, built from triggers and steps.
ManusA general-purpose agent that researches and builds documents, slides, sites and videos in its cloud, with a desktop app that can work in approved local folders.
LovableA prompt-to-app builder: describe a web app, get a hosted React front end with a built-in backend, edited by chat.
Base44Wix-owned prompt-to-app builder with backend, auth and hosting included, metered in messages and integration credits.
OpenClawOpen-source personal agent that runs on your own machine and answers in WhatsApp, Telegram, Slack and 20+ other chats, bring your own keys.
Hermes AgentOpen-source self-improving personal agent from Nous Research: skills it writes itself, memory that persists, reachable from 20+ chat apps.
LinearThe issue tracker engineering teams like, with its own Linear Agent and coding sessions in a Linear sandbox.
NotionThe docs-and-databases workspace, with Custom Agents that run on schedules and triggers inside it.
ClickUpAll-in-one work platform whose Super Agents can be @mentioned and assigned tasks like teammates.
AsanaWork management with assignable AI Teammates, Dash, and a no-code studio for cross-system workflows.
Copilot CoworkMicrosoft 365 Copilot's agent: describe a task and it does the work across Outlook, Teams, Word, Excel, PowerPoint and SharePoint.
GitHub CopilotGitHub's coding agent: completions in the editor, a cloud agent that takes an issue and opens a pull request.
monday.comWork OS whose AI agents sit in board columns and automations, metered in AI credits.
ZapierThe largest integration network, plus Agents you can chat with on a separate activity meter.
MakeVisual scenario builder with credit-metered runs and AI agents on every plan.
n8nFair-code workflow automation you can self-host, priced per whole workflow run.
AirtableDatabase-shaped workspace whose Omni agents build apps and act on records, metered in AI credits.
MotionAI calendar and task manager that schedules your work for you, credits included per seat.
TrelloThe simplest kanban board, with AI that summarises and organises cards rather than working them.
GumloopAI-native automation for business teams: chat-driven agents plus flows, priced in credits.
Or start from your job
The same tools rank differently depending on who is buying. Each guide weights the scores by what that job actually needs.
Common questions
Found a cell that is wrong? Tell us and we will change it.