Issue Trackers
Linear issue #243
Linear issue #253 (blocked)
Linear issue #248 (done)
Issue #210 (blocked)
Issue #219 (gateway scope)
PR #456 (merged)
+ more
Slack said one thing. GitHub said another.
Thor keeps GitHub and Linear up to date with what the team decided in Slack and Zoom. You approve. Your agents build.
Shipping got fast. Coordination didn't.
Context doesn't break. It rots. A decision gets made in a meeting, then changes in a Slack thread, and the spec, issue, and branch all disagree. Nobody lied, the org just moved faster than its own record.
Code now ships in minutes. The decisions and reviews around it haven't caught up. That's exactly where Thor closes the gap.
Context Graph
Before
Every agent — Claude Code, Cursor, Codex — starts from zero, every session.
With Thor
One shared context graph every agent and every person can query.
Cursor — new session
AGAIN
Agent —
what's our auth architecture? Who owns the gateway?
Asked for the 4th time this month.
Thor — Context Graph
CTX-118
Auth service — the full picture
Decision history
Owners
Open blockers
Day-Zero — before build
Before
Agents build from whatever's in the prompt, right or wrong.
With Thor
Agents build from a spec that's already been questioned against your team's real history.
Feature PRD.md — v1
JUST NOW
Spec —
ready to build.
One untested assumption inside.
Thor — Spec Review
SPEC-42
Your team tried this in Q1
Decision #142
2 clarifying questions
Day-Zero — while building
Before
Nobody notices requirements drifted until sprint review — weeks of work, wrong direction.
With Thor
Thor flags the drift the moment a thread or meeting contradicts what's being built.
From #product
2H AGO
Priya —
heads up, we descoped the bulk-import flow last week.
The spec never changed.
Thor — Drift Alert
ONB-214
Active work contradicts a decision
Drift flagged
Spec vs #product
Get Your Time Back
Before
Someone manually turns meetings into tickets, chases follow-ups, writes standups.
With Thor
Thor does it automatically, because it already has the context.
Sprint planning — transcript
MON 9:14
Notes —
47 minutes of decisions, follow-ups and action items.
Someone types these into tickets by hand.
Thor — Standup
AUTO
Standup written, tickets created
5 tickets
3 follow-ups
Standup drafted
Powered by a context graph of your projects
Thor doesn't just connect to your tools. Thor builds a graph of how people, teams, and projects connect across GitHub, Linear, Slack, meetings, and more.
Docs & Specs
+ 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
What did the team ship this week?
Team Updates & Recaps
Drift Notification
Drift Notification
Generated Specs & Tasks
PR description & test plan
DraftAgents & Apps
One record, kept current, served everywhere.
Thor turns scattered work into a living record, keeps it current, and serves the right context wherever work happens.
Canonical Record
What the org is actually working on, in structured form. Every decision, every commitment lives here.
Launch Readiness
Decision
Ship on Aug 10
Commitment
Finalize GA scope
Owner
Jason Kim
Status
On track
Slack
Github
Docs
Operating Layer
Keeps the record current as work moves. Ingests signals, diffs against the record, proposes updates.
Signal ingested
Diff proposed
Approved
Record updated
Context Engine
Makes the record useful to every human and agent. Swap in a new tool and it feeds it without reconfiguration.
Correct context, automatically
Human
Agent
New Tool
Clear about what it isn't
Not a coding agent
Doesn't write code.Doesn't replace the coding agents your engineers use. Feeds the ones you already use.
Gives it the context it's missing.Claude Code, Cursor, whatever your team runs.
Not a meeting summarizer
A summary isn't the point.Notes are a byproduct, not the goal.
Knows what was actually decided.Understands well enough to act on it, not just recap it.
Not a project management tool
Doesn't replace Linear or Jira.Sits underneath them, not another board to maintain. Keeps your board honest automatically.
Updates it without anyone touching it by hand.Runs underneath, stays accurate on its own.
Not a chatbot
You don't open it and ask it things.No prompt required to get value. Works without being asked.
Only shows up when something needs you.Background by default, not another window to check.
Ask Thor anything.
Get answers right away
Thor has the complete picture of what your team is working on. Ask Thor anything you'd ask a teammate, and get an instant, accurate answer.
Y
You
Just now
What has George been working on?
T
Thor
Thinking...
T
Thor
Just now
Here's what George has been working on this week:
- Completed PR #456 for authentication refactor (merged Tuesday)
- Currently reviewing database migration plan in #eng-backend
- Opened Linear issue #789 for Redis caching implementation
- Had 3 meetings: Sprint planning, Architecture review, 1:1 with Tyler
T
Thor
Just now
Yes, 3 engineers are currently blocked:
- Sarah is waiting on a review for PR #234 (API rate limiting refactor), open for 2 days with Marcus and Dev tagged as reviewers
- James has PR #301 (payment webhook integration) pending review since yesterday, flagged as high priority but with no reviewers assigned yet
- Priya is blocked on the new onboarding flow implementation until the product spec in Notion is approved, waiting on sign-off from the PM team
T
Thor
Just now
Here's the current status of the database migration:
- Overall progress: 8 of 12 issues complete
- Sarah Chen completed the schema conversion for the users table yesterday and has moved on to the orders table
- James Okafor is currently running validation scripts on the migrated data from Phase 6, with results expected by EOD
- Next milestone: Full staging environment cutover scheduled for Thursday
- Risks: 2 tables have unresolved warnings that need review before production cutover
T
Thor
Just now
Here's a quick brief to help you prep for your 1:1 with George:
What George has been working on George completed PR #456 for the authentication refactor (merged Tuesday) and opened Linear issue #789 for the Redis caching implementation. He's currently reviewing the database migration plan in #eng-backend.
Potential talking points
- PR #612 (error handling improvements) has been open for 4 days without a reviewer assigned, worth checking in on
- George left a comment on the architecture review doc flagging concerns about the proposed caching strategy, may be worth discussing
- His last 3 PRs have averaged 3 days to review, which is above the team average
Wins to acknowledge
- The authentication refactor he led shipped cleanly with no post-merge issues
- He proactively flagged a potential bottleneck in the migration pipeline last week
Open questions you might want to ask
- Is he still on track for the Redis caching ticket given the current migration workload?
- Does he need any support getting reviewers on his open PRs?
T
Thor
Just now
Your last meeting on the database migration was Tuesday, February 11th at 2:00 PM.
- Attendees: Sarah, James, Priya Nair, Tyler (PM), and you
- Duration: 47 minutes
- Key decisions made: Agreed to prioritize the orders and users tables before moving to the analytics tables, and confirmed Thursday as the target date for the staging environment cutover
- Action items from that meeting: James to run data validation scripts by EOD Friday, Sarah to document schema conversion process for handoff, Tyler to get sign-off on the analytics table spec from the PM team
- Note: 2 action items from that meeting are still open, James's validation results are in and Sarah's documentation is still pending
T
Thor
Just now
Here's what I found and added to Linear Issue #123 (Redis Caching Implementation):
Description updated with the following context:
- From the Architecture Review meeting (Feb 13th): George flagged concerns about cache invalidation strategy for user session data, specifically around edge cases where multiple services write to the same key. The team agreed this needs to be resolved before implementation begins.
- From #eng-backend (Feb 14th): Marcus shared a link to an internal doc outlining the proposed TTL values for each cache layer. James replied suggesting a shorter TTL for the orders service given its write frequency.
- From the Sprint Planning meeting (Feb 10th): This ticket was flagged as a dependency for the payment webhook integration (PR #301), meaning a delay here could push back James's work as well.
Get going in a few minutes
STEP 01
Connect your tools
Link Thor to GitHub, Linear, Slack, Google Meet, and Drive. Takes 2 minutes.
STEP 02
Invite Thor to Slack
Add Thor to the Slack channels and meetings where your team coordinates work.
STEP 03
Thor starts working
Thor begins building your context graph and handling coordination automatically.
See what Thor keeps moving for you.
One shared record. A different advantage for every team.
For Leaders
Thor tracks commitments, surfaces what needs you, and keeps the whole picture current.
Explore Thor for leaders
For Engineers
Thor loads the decisions, constraints, and history your coding agents would otherwise miss.
Explore Thor for engineers
For Product
Thor carries forward what was tried, ruled out, and decided — before the team commits.
Explore Thor for product
For AI Partners
Thor keeps every AI implementation's decisions and status straight, and leaves each client with a context layer of their own, not just a training deck.
Explore Thor for AI partnersFAQs
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.
How does Thor handle permissions and data access?
For tools that connect per person (GitHub, Linear, Google, and Notion), Thor uses that person's authorization. If you cannot see a repository or a document, Thor cannot see it through your connection. Slack connects once for the workspace, and Thor's bot only sees channels it has been added to. A system you connect yourself, such as your own MCP server, uses one organization credential set up by the person who configures it. Thor does not sign in to that system as each Slack user, and there is no per-person token in Thor for that connector to rotate.
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.
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.
What if I use a tool that isn't on your integrations list?
We are constantly expanding our ecosystem of connected tools based on customer feedback. If you have a specific tool you'd like us to support, we'd love to hear about your use case. Please reach out to our team at support@thor.ai.
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.
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.