# ecco vs. t0ggles: Which agent board is best for your work? [2026]

_ecco and t0ggles are both boards your AI agents work from. ecco enforces evidence and decision rules on every agent, however it connects. How they compare._

By Saad Ahmed, 2026-10-01. Facts about t0ggles checked 2026-10-01.

## Choose ecco if

- You want every agent to attach evidence before its task counts as done, however it connects
- You want one inbox of decisions that only a person in your workspace can answer
- You run several agents and want each task claimed by one of them at a time

## Choose t0ggles if

- You want Gantt charts, calendar views, notes and forms in the same tool
- You want a desktop app that runs your agents for you in chained pipelines

Of all the tools ecco competes with, t0ggles is the closest. Its page for AI agents is titled "Task Management for AI Agents: Human-in-the-Loop Boards," and that could almost be ecco's tagline.

t0ggles comes from Vladimir Kharlampidi, who built Swiper and Framework7, two open-source tools a lot of developers rely on. It shows. Agents connect to t0ggles over MCP with a browser sign-in, each agent gets its own named identity on the board, and every change is recorded under the identity that made it.

I think the honest comparison is narrow. Both products put agents and people on one board. Both care about keeping a person in the loop. The difference is where that loop lives: in t0ggles, it's a workflow you design; in ecco, it's a set of evidence and decision rules the board enforces on every agent.

This comparison is for people deciding between the two for work their agents do.

## ecco vs. t0ggles at a glance

|  | ecco | t0ggles |
| --- | --- | --- |
| Built for | People handing work to AI agents | Projects for teams and their AI agents |
| How agents connect | Remote MCP with OAuth; read-only or write per agent | Remote MCP with OAuth; a named bot identity per agent |
| Running agents | You run your own agents; ecco never runs a model | Crew, a free desktop app, runs Claude Code, Codex and OpenCode for you |
| Marking work done | Agents must attach a PR, commit or evidence reference first | Review steps you design; Crew agents wait for a person to reassign |
| When an agent needs a decision | One inbox; only a signed-in person in your workspace can answer | A review status plus notifications you set up |
| Two agents, one task | One live claim per task; claims expire if not renewed | Assignment; no locking described on its agent page |
| Planning tools | Tasks, projects and initiatives, kept simple for agent work | Gantt, calendar, templates, notes, forms, custom fields, automations |
| Price | Free in beta; then $79 a year per workspace | Free plan; paid $5 per user a month, billed yearly |

## t0ggles lets you design a review step; ecco refuses an agent's "done" without proof

t0ggles' approach to review is thoughtful. Here's how a Crew pipeline runs. A planner agent writes a plan. A reviewer agent checks it and hands it to you. You approve it and pass it to a developer agent. The developer opens a pull request, and it comes back to you before anything merges. As t0ggles puts it, "the agent cannot proceed past a review step until a person reassigns the task."

My sense is that this works well when your agents run through Crew and the workflow is set up that way. ecco takes a different route. The rule sits in the board itself, so it applies to any agent from any client. An agent can't move a task to review or to Done until it attaches a reference to the work: a pull request, a commit, or an evidence record. Evidence records you've rejected don't count. A reference doesn't prove the work is good, but it gives you something specific to check. People can still close their own tasks; the rule is for agents.

**What it's worth:** the evidence step doesn't depend on how a workflow was set up. Every task an agent finishes carries a reference you can check, which makes checking faster.

## t0ggles notifies a reviewer; ecco gives every decision one inbox only a person can answer

In t0ggles, an agent moves a task to a review status and an automation can notify the person assigned to review it. That's a solid pattern for handoffs.

ecco is built for the questions in between. Those come up all day. When a call belongs to you, the agent writes the question on the task with its options, the one it recommends, and why it didn't pick the others. Every open question from every agent lands in one inbox.

Two rules make that inbox trustworthy. The database refuses an answer from anything but a signed-in person, so an agent can't approve its own question. And if what the question was about changes before you answer, your answer is refused as stale, so no agent acts on a decision made against an older picture of the work. Agents can also withdraw a question you've already settled with them in chat. That rule came from my own complaint: "Why am I being asked in Inbox?"

**What it's worth:** your interruptions are limited to decisions that are still open, and agents can't answer their own questions.

## t0ggles assigns tasks to agents; ecco gives each task one live claim

In t0ggles, agents find their work by listing the tasks assigned to their bot user, and they start by moving a task to In Progress. I couldn't find anything on t0ggles' agent page that stops a second agent from starting the same task.

In ecco, an agent claims a task before it works on it, and only one live claim is granted per task. The agent that loses is told who has the task, so it can pick up something else. Claims expire after five minutes by default unless the agent renews them, so if an agent crashes halfway through, its claim expires and another agent can take the task.

Each agent also gets its own access: read-only or able to change tasks. A workspace admin can revoke it from the Workers page, and that connection is cut off on its very next request.

**What it's worth:** claims can cut the tokens you spend on two agents doing the same job, a crashed agent's claim doesn't lock the task, and you can let a contractor's agent onto your board with only the access it needs.

## ecco is focused on the rules your agents work under

t0ggles covers a wide range for project work: Gantt charts, calendar views, task templates, notes, forms, custom fields and automations, plus Crew, a desktop app that runs agents for you.

ecco puts its effort into one thing: the rules every agent works under, whichever tool runs it. You bring the agents you already use, like Claude Code, Codex or your own, and ecco holds all of them to the same rules. Evidence before done, decisions only a person can answer, and one live claim per task. The board stays simple: tasks, projects and initiatives, and one inbox.

## t0ggles charges per person; ecco charges per workspace

t0ggles has a free plan with one board, three team members and 100 tasks per board, and it includes the MCP server and Crew. The paid plan is $5 per user a month, billed yearly, with unlimited boards, projects and tasks. On the paid plan, that's $60 a year for one person and $300 for five.

ecco is free while it's in beta. After the beta it's one plan: $79 a year per workspace, for up to 5 people and 25 connected agents. For two to five people, ecco costs less than t0ggles' paid plan, and the price already covers 25 connected agents. t0ggles also has a free plan for up to three members.

## ecco or t0ggles: which should you choose?

I think the choice comes down to one question: do you want the tool to run your agents, or to hold them to rules?

If you already have your agents and want every one of them held to the same rules, choose ecco. Every task an agent finishes carries evidence you can check, every decision waits for a person, and each task has one live claim. After the beta it's $79 a year for a whole workspace of up to 5 people and 25 agents.

If you want a broad project tool that also runs agents through its own desktop app, t0ggles is built for that.

Weighing other tools too? Read [ecco vs. Linear](/blog/ecco-vs-linear), [ecco vs. Plane](/blog/ecco-vs-plane) and [ecco vs. Claude and ChatGPT on their own](/blog/ecco-vs-claude-and-chatgpt). Ready to try it? Here's [how to use ecco with Claude Code](/blog/ecco-with-claude) and [how to use ecco with ChatGPT and Codex](/blog/ecco-with-chatgpt).

## Frequently asked questions

### Is ecco a t0ggles alternative?

Yes, if what you need is a board that holds every agent to the same rules: evidence before a task is done, decisions only a person can answer, and one live claim per task.

### Do both work with Claude Code and Codex?

Yes. Both connect over MCP with a browser sign-in. t0ggles' Crew can also run Claude Code, Codex and OpenCode for you; with ecco you run your own agents.

### How much does ecco cost compared with t0ggles?

ecco is free during the beta, then $79 a year per workspace for up to 5 people and 25 agents. t0ggles has a free plan for up to three members, and its paid plan is $5 per user a month billed yearly: $60 a year for one person or $300 for five.

### Can two agents work on the same task in ecco?

Only one agent can hold a live claim on a task. Claims expire after five minutes by default unless renewed; if an agent stops responding, its claim expires and another agent can claim the task.

We make ecco. Report outdated facts to saad@cosmiclabs.net.

## Sources

- [t0ggles for AI agents](https://t0ggles.com/for/ai-agents)
- [t0ggles pricing](https://t0ggles.com/pricing)
- [t0ggles Crew](https://t0ggles.com/crew)
- [About t0ggles](https://t0ggles.com/about)
- [t0ggles blog: Introducing the free plan](https://t0ggles.com/blog/introducing-the-free-plan)