Your agents outpace your board. Your AI project manager keeps up.

Thor keeps your backlog, issues and roadmap current as plans change. You ship more, and nothing slips through the cracks.

Get Started

Shipping got fast. Coordination didn't.

Most software teams don't have a project manager. Someone does the job on the side: filing issues after meetings, cleaning up the backlog, checking work against the roadmap.

Thor picks up that work, so the person stuck with it can get back to building.

Meetings to issues

Every action item from the meeting, filed right.

Thor reads the transcript from Google Meet or Zoom and picks out the real action items, not every passing comment. It checks your GitHub or Linear issues first, so it updates the ones that already exist instead of filing duplicates. Each issue has an owner and a link back to the moment it was said. You approve them in Slack with one click.

4 issues from Sprint planning

Tue 10:00 · 47 min transcript

  • Add retries to webhook delivery@Priya
    Create issueRemind me
  • Rewrite the Teams install copy@Sam
    Create issueRemind me
  • Spike: bulk import on large CSVs@Jerry
    Create issueRemind me
  • Move bulk import UI to next cycle✅ Already logged in Bulk import UI for onboarding
    Add commentRemind me

Backlog cleanup

Clear out the tickets nobody wants to go through.

Thor goes through your GitHub or Linear backlog and finds the tickets that already shipped, repeat each other or went stale. It drafts the cleanup with a reason for each one. You approve, and Thor closes or merges them.

18 tickets to close or merge

From 214 open in your backlog

6 already shipped4 duplicates8 stale
  • Add CSV export to bulk importAlready shipped in PR #1188
    Close
  • Webhook retries fail on timeoutSame as LIN-471
    Merge
  • Explore SSO for the enterprise trialNo activity since March
    Close

Roadmap check

See which work moves the roadmap, and which doesn't.

Thor reads your roadmap and checks every open issue against it. Work that ties to a goal gets grouped under it. Work that doesn't gets flagged, so you can decide what stays before the sprint fills up with it.

Q4 roadmap check

46 open issues, checked against 2 goals

  • Self-serve onboarding by December18 issues
  • Billing v2 migration21 issues
  • 7 issues don't map to any goalRedesign the settings page · Dark mode for the dashboard · 5 more

Better issues

Issues written like your best engineer took the notes

Ask Thor to file an issue, and it does the digging first. It checks GitHub or Linear and flags any duplicates. It adds what was decided in recent meetings and links related PRs and threads, so whoever picks it up starts with the full picture.

Webhook retries fail silently

New issue, drafted from your message in #eng

  • Possible duplicateLIN-471 · Webhook delivery drops on timeout
  • From Tuesday's planning callBack off between retries, stop after 5 attempts
  • RelatedPR #1290 by @Priya · Slack thread in #eng-alerts
Create in LinearAdd to LIN-471

Your automations

Write your own automations, and bring Thor to your coding agent.

Tell Thor what you want done and when, in plain English, and it runs on that schedule. Connect Claude Code, Cursor or Codex to Thor through MCP, and your agent starts from your team's issues, decisions and history instead of a blank prompt.

Your automations

Written in Slack, run by Thor

  • Every Friday, 4pmPost a recap of what shipped to #leadership
  • After every planning callFlag any issue without an owner
Claude CodeCursorCodex

> Pick up LIN-482. Check Thor for what was decided first.

Thor MCP · 3 decisions, 2 related PRs, owner @Priya

How your AI project manager knows what changed

Every update Thor drafts comes from its context graph. That's a live map of who's working on what and what was decided, across GitHub, Linear, Slack and your meetings.

Issue Trackers

Linear issue #243
Linear issue #253 (blocked)
Linear issue #248 (done)
Issue #210 (blocked)
Issue #219 (gateway scope)
PR #456 (merged)
+ more

Docs & Specs

NotionGoogle DocsGitHub Markdown
Auth Architecture Spec
Gateway Migration Plan
design-system.md
Feature PRD v2
+ more

Video Meetings

Sprint Planning
Sprint Demo & Review
Daily Standup
Architecture Sync
Engineering All-Hands
Design Critique & Review
Product Sync
Security Review Call
+ more

Chat Platforms

#eng-platform thread
#standup (yesterday)
Project handoff thread
#product (drift warning)
Engineering Channel chat
General Standup thread
Release handoff post
Product Team (scope shift)
+ more
Thor's context graph

What did the team ship this week?

Data Cleaning
Context Graph
Classification
De-duplication
From the context graph, Thor keeps issues current, writes work recaps and follows up after meetings, for your team and its AI agents.

Team Updates & Recaps

Stakeholder Approval
Sprint Review Digest
Meeting Recap in Thread
Drift Notification
Stakeholder Approval
Status Review Digest
Meeting Recap Card
Drift Notification

Generated Specs & Tasks

GitHub Issue #245
Auto-created
Linear ticket ENG-382
Synced
Auth-Architecture-v2.md
Spec
PR description & test plan
Draft

Agents & Apps

MCP
CursorCoding Agent
MCP
Claude CodeCoding Agent
Slack App
Thor Slack BotAI Teammate
Teams App
Thor Teams BotAI Teammate

Thor is not...

A chatbot you have to prompt

Thor doesn't wait for you to ask.Thor spots what changed and drafts the update without being asked.

Only shows up when something needs you.And when you do want to ask, it already knows the answer.

A new board

Thor works in the GitHub or Linear board you already use.No new tracker to move to, and nothing to migrate.

It doesn't change anything on its own.Thor drafts the update. You approve it before it lands.

A meeting summarizer

A summary isn't the point.Thor treats notes as a byproduct.

Thor knows what was actually decided.It drafts the issues and tags the owners, so the decision doesn't stay in the meeting.

A coding agent

Thor doesn't write code.Your engineers keep the coding agents they already use.

It gives those agents the context they're missing.Claude Code, Cursor or Codex starts from what your team decided, not a blank prompt.

Get going in under 5 minutes

STEP 01
Connect your tools

Link Thor to GitHub, Linear, Slack, Google Meet, and Drive. Takes 2 minutes.

STEP 02
Bring Thor into the conversation

Add Thor to the Slack or Teams channels and meetings where your team plans work.

STEP 03
Thor starts working

Thor builds its context graph of your team and starts keeping your issues current. You'll hear from it when something needs you.

See what Thor keeps moving for you.

One AI project manager. A different job off every team's plate.

For Engineers

Your issues stay current without the grooming, and your coding agents get the decisions and history they'd otherwise miss.

Explore Thor for engineers

For Product

Thor turns planning calls into issues and remembers what was tried, ruled out and decided, before the team commits.

Explore Thor for product

For AI Partners

Thor keeps every AI rollout's decisions and status straight, and leaves each client with a context graph of their own, not just a training deck.

Explore Thor for AI partners

FAQs

What is Thor?
Thor is your AI project manager for software teams. It does the work project managers do: organizes the backlog, keeps tickets and boards up to date, coordinates across your tools, and keeps the roadmap aligned. It's powered by Thor's context engine: one living record of what your team decided, kept current from Slack, meetings, GitHub, Linear, and your docs, so the next person or coding agent never starts from a guess. Thor drafts the updates that keep that record honest, and a person approves them before anything official changes.
What is an AI project manager?
An AI project manager does the upkeep a project manager would. It turns meetings into issues, keeps tickets current when plans change, follows up on work that stalls, and checks work against the roadmap. Unlike a chatbot, it doesn't wait to be asked. Thor is an AI project manager for software teams. It works in GitHub, Linear, Slack, Teams and your meetings, and a person approves every change before it lands. Our guide covers what an AI project manager does for software teams, step by step.
Who is Thor built for?
Thor is purpose-built for software engineering and technical teams that are moving too fast and feeling overwhelmed with administrative overhead. It's ideal for team leads, engineering managers, and founders who feel the pain of coordination tax most acutely.
Does Thor change things on its own, or do I approve first?
Thor proposes and a person approves. Thor drafts the change, a new issue, a new owner, a status update, a doc edit, shows you where it came from, and waits for someone to accept it before anything in your tools changes. Nothing becomes official just because an AI sounded sure.
How is Thor different from ChatGPT or a general AI assistant?
Thor doesn't wait to be asked. A general assistant answers from whatever you paste into the chat, so two people asking the same question can get two different answers, and nothing gets written down as decided. Thor reads the work itself, keeps one shared record of what's decided and what's gone stale, and comes to you when a commitment is aging or a ticket no longer matches what the team agreed. Every answer shows where it came from. General AI assistants are designed to answer general questions, from medical diagnosis to child care to weather reports. Thor is focused on a narrow mission: keeping your team's work honest and up to date.
Do I have to invite another bot to all my meetings?
Nope. You have enough bots to deal with. Thor isn't an awkward guest you have to remember to add to every call. It works by hooking into the meeting transcripts your team already generates in Google Meet, Zoom, and Microsoft Teams.
Do I need to be a workspace admin to set up Thor?
Not at all. You can initiate the setup in minutes using standard, secure third-party authorization like GitHub OAuth. If an integration requires broader admin approval, Thor will provide a simple, shareable link for your workspace admin to grant the necessary permissions.
What is the pricing for Thor?
Every plan gets unlimited people, meetings, and connected tools. You only pay for actions, which are the finished things Thor produces: a ticket created, a doc updated, a question answered. Free is $0 with 25 actions a month, Team is $199 with 300, and Enterprise is custom. See thor.ai/pricing for the full breakdown of what counts.
How does Thor turn meetings into tasks?
After your meeting ends, Thor reads the transcript and figures out what actually needs to happen next. Then Thor drafts a plan: either the action items can be converted to issues, or a document update can be triggered to capture any decisions that were made, or Thor can follow up with Sarah about that API thing you discussed on the call but already forgot about. You look over Thor's suggested next steps, give it the thumbs up, and Thor actions it. Nothing lands in your tracker until someone says yes. Transcription needs to be switched on in Google Meet or Zoom, since Thor never joins the call.
How accurate is Thor with technical conversations?
Thor is specifically tuned for software development and product team conversations. However, our key feature is the "human-in-the-loop" design. Thor always proposes a plan for your approval before taking any action, giving you the chance to add any necessary nuance or corrections.
Will this create more notification spam for my team?
No, the opposite. By centralizing follow-ups and creating structured action plans, Thor reduces the random "just checking in" pings on Slack. You can configure how and when Thor communicates to fit your team's existing workflow and minimize unnecessary noise.
How does Thor protect my data?
Thor is SOC 2 Type II compliant, and we've completed a Cloud Application Security Assessment (CASA), the App Defense Alliance standard for apps that access sensitive Google user data. Thor is a new product from the team behind Zenhub, who have a decade-long track record of building enterprise-grade developer tools with security at their core. We apply the same standards to everything we build.
Do you train your AI models on my company's data?
Absolutely not. Your data is yours alone. We never use customer data, conversations, or meeting transcripts to train our models.
Does Thor have access to read or write our source code?
No. Thor's integration with tools like GitHub is strictly limited to project management functions like creating, updating, and commenting on issues. It has read access to your codebase in order to understand the context of the work and access the relevant documentation (typically stored in markdown files). Thor cannot push directly to your codebase.
Is there an audit trail for actions taken by Thor?
Yes. The conversation record stores who asked, which tool ran, and what came back. We can provide that record on request. It is not a screen in the product yet. On GitHub and Linear, a write uses the authorization of the person who asked, when they have connected that tool, so the tool's own history shows them. A system you connect yourself is written as the organization credential, so that system's history shows the credential, not the Slack user.

See all