Your AI agent can work in Thicket
The whole product runs on a documented REST API, and the web app uses the same routes. Anything the team does in Thicket, an agent with your permission can do too: post updates, work the to-do lists, file documents, move cards, answer check-ins.
Free plan available. No credit card required.
Quick facts
Thicket for AI agents, in plain terms
Thicket is simple flat-rate project management for small teams. Its entire feature surface is exposed through a versioned REST API, so AI agents can work inside your projects today: no plugin, no marketplace, no extra fee.
- Agent access
- Every feature has an API route under /api/v1. The web app runs on the same routes, so what an agent can reach never lags the product.
- Authentication
- Email sign-in sets a session cookie that works for every call. Personal access tokens are planned and slot in without route changes.
- What it costs
- Nothing extra. Pro is $49/month flat with unlimited people, so giving an agent its own account never raises the bill.
- Built-in AI
- None, on purpose. Thicket ships no AI features. You bring whichever agent you already trust: Claude, ChatGPT, Copilot, Gemini.
- JSON everywhere: snake_case keys, no response envelope, consistent error objects.
- One content model: messages, to-dos, docs, files, cards, and chat lines share a single recording lifecycle.
- Organization-level isolation enforced in the database with row-level security.
- Roles scope what an agent sees: member for teammates, client for view-limited outsiders.
- Owners can export the whole account as JSON at any time.
- Machine-readable site guide at thickethq.com/llms.txt.
What an agent can do in a project
Every Thicket project has a message board, to-dos, docs and files, a schedule, boards, and chat. An agent reaches all of them through the same API the app runs on.
Post and read updates
Write the weekly summary on the message board, publish meeting notes, or read every thread it has access to and report back.
Work the to-do lists
Create lists and to-dos, assign people, set due dates, and check things off. Recurring to-dos keep the routine chores rolling.
Keep docs and files current
Write rich documents, upload files, and replace a file with a new version while the comments and subscribers carry over.
Move work across the board
Kanban cards move between columns with one position update, so an agent can triage incoming work or clear a done column.
Run the schedule
Create events with recurrence and reminders, read what's due this week, and shift dates when a project slips.
Answer and digest check-ins
Post its own answer to a recurring question, or read everyone else's answers and turn them into a digest.
Search and report
Full-text search across everything the agent can access, plus ready-made reports: overdue to-dos in lateness buckets, upcoming schedule items, each person's open assignments, and the account-wide activity timeline. An agent can answer "where are we?" without you assembling anything.
A working session, in four calls
This is the real surface, not pseudocode. Any agent that can run shell commands can do this today with curl and a cookie jar.
# 1. Sign in once; the session cookie authenticates everything after
curl -c cookies.txt -X POST https://www.thickethq.com/api/auth/sign-in/email \
-H "Content-Type: application/json" \
-d '{"email": "agent@yourteam.com", "password": "..."}'
# 2. Find the project's tools (each tool has a container id)
curl -b cookies.txt \
https://www.thickethq.com/api/v1/acme/projects/$PROJECT_ID/tools
# 3. Post a status update to the message board
curl -b cookies.txt -X POST \
https://www.thickethq.com/api/v1/acme/recordings/$BOARD_ID/children \
-H "Content-Type: application/json" \
-d '{"type": "message", "title": "Week 33 summary", "content": "..."}'
# 4. Check off a finished to-do
curl -b cookies.txt -X PUT \
https://www.thickethq.com/api/v1/acme/recordings/$TODO_ID/completionThe full reference, with every route, lives at thickethq.com/developers/api. It's one page: an agent can read the whole thing in a single pass.
Why agents do well here
One content model, few special cases. Messages, to-dos, documents, files, board cards, and chat lines are all recordings: one lifecycle, one comment system, one way to move things. An agent that learns the pattern once can operate the whole product, instead of memorizing a different API for every feature.
The API can't drift from the product. The web app is built on the same service layer and the same routes. There is no separate integration surface that lags a release behind; if a feature ships, its API shipped with it.
Predictable JSON, honest errors. snake_case keys, no envelope, and a consistent error object. A 402 tells an agent it hit a plan limit, a 422 tells it what to fix, and a 404 means the thing isn't there or isn't yours. Nothing to guess at.
Everything is attributed and reversible. An agent works from its own account, so the project timeline shows exactly what it did, next to what everyone else did. Anything it trashes can be restored for 30 days. If an agent makes a mess, you can see it and put it back.
Tenancy is enforced below the code. Every request runs against row-level security in the database. An agent's session in your organization returns nothing from anyone else's, the same guarantee your own session has.
Agents don't change the math
Per-seat tools have an awkward question coming: is an agent a seat? Thicket never has to ask. Pro is $49/month for the whole organization, people and agents alike, so you can give an agent its own account for clean attribution without doing arithmetic first.
Point an agent at Thicket today
- 1
Give the agent an account
Invite something like agent@yourteam.com the way you'd invite a person. Its own account keeps the timeline honest: you always know which work was the agent's. On Pro, people are unlimited; on the Free plan the account counts toward the 20-person limit.
- 2
Scope what it can reach
Add it to the projects it should work in and no others. Make it a member for normal work, or a client if it should only see what the team chooses to share.
- 3
Hand it the reference
Give your agent the docs URL (thickethq.com/developers/api) and the account credentials. Agents that run shell commands need nothing else: sign in, keep the cookie jar, work.
- 4
Watch it work
The project timeline shows every action under the agent's name. Anything it deletes sits in the trash for 30 days, so a wrong move is an undo, not an incident.
No AI inside, on purpose
There's no chatbot docked in the corner of Thicket, no AI summary button, no credits meter. That's a decision, not a gap. The agents you already use, Claude, ChatGPT, and whatever comes next, get better every month without us shipping a thing, and they're already where you work.
So we spend our effort where it compounds: a clean data model, an API that covers the whole product, and a workspace calm enough that both people and agents can find what they need. When AI helps your team, it walks in through the front door with its own account, and you stay in charge of what it touches.
Where this is going
The API is the foundation, and it's live. Three additions are scheduled on the same build ledger the rest of the product ships from. This page will say so plainly when each one lands.
Personal access tokens
Scoped tokens so an agent never handles a password. The API was designed for them; they slot in without route changes.
A command-line tool
Plain commands over the same API, with JSON output built for agents, so "add this to the launch list" is one line in any shell.
An agent skill pack
A short instruction file that teaches an agent Thicket's patterns up front, instead of leaving it to work them out from the docs.
AI agents and Thicket
Can Claude or ChatGPT use Thicket?
Any agent that can make HTTP requests can drive Thicket end to end: Claude Code and similar coding agents do it with curl and a cookie jar. A chat assistant that can't execute code can still read the API reference and this page to walk you through anything. Thicket's own reference lives at thickethq.com/developers/api, and the site publishes a machine-readable guide at thickethq.com/llms.txt.
Does Thicket have built-in AI features?
No, and that's deliberate. There's no chatbot in the corner, no AI summary button, no credits meter. The agents you already use improve every month without us shipping anything, so we put our effort into the API they work through and keep the product itself calm.
Do AI agents cost extra?
No. Thicket Pro is $49/month flat with unlimited people, so giving an agent its own account changes nothing on the bill. On the Free plan an agent's account counts toward the 20-person limit like anyone else.
How does an agent authenticate?
The same way the web app does: signing in with email and password sets a session cookie, and every /api/v1 call accepts it. An agent signs in once, keeps the cookie jar, and works. Personal access tokens are planned, and the API is built so they slot in without route changes.
Is there a CLI or MCP server?
Not yet. Today the surface is the REST API, which covers the entire product. A command-line tool designed for agents, personal access tokens, and an agent skill pack are on the build ledger; this page will say so plainly when each one ships.
How do I control what an agent can see and do?
The same way you control a person. Project membership decides which projects it can enter, and its role decides what it can touch: a member works normally, a client sees only what the team shares. Every action is attributed to the agent's account in the project timeline, and anything it deletes sits in the trash, recoverable, for 30 days.
Put a project where your agent can help
Set up a project, invite the team, and point your agent at the API. If having an extra set of hands on the admin doesn't make the week calmer, nothing is lost.
Free plan, no credit card required
$49/month flat on Pro, agents included
The full REST API from day one