Free
For solo developers and small teams trying VectorGraph.
$0/ user · month
Free, forever, no card required.
Create workspace- 300 issues per workspace
- Up to 2 teams
- Unlimited members
- Code-linked work
- First-party CLI and MCP
Company context and execution
AI-native work management for software teams
VectorGraph connects issues, customer signal, docs, pull requests, and local code intelligence into one permissioned work graph. Humans use the UI, scripts use the CLI, and AI agents use MCP, all with the same scopes, context, and audit trail.
Create work. Connect context. Give agents scoped access. Ship with an audit trail.
What it is
A company context and execution layer for AI-assisted engineering teams, starting with fast work management.
What is different
Most trackers were built for humans only. VectorGraph was built so humans, scripts, and agents can work from the same context and rules.
Why now
AI agents can write code, but they still need structured work context, scoped permissions, local code intelligence, and evidence before teams can trust them.
Built in
Built for human and agent collaboration
Plan the work, keep the context beside it, and give humans, scripts, and agents the same scoped view of what changed and why.
Work management
Issues, projects, sprints, initiatives, templates, reminders, saved views, inbox, private teams, and audit-backed activity.
Customer signal
Signal intake, requester status, customer-request links, SLAs, and close-the-loop notification records connected to shipped work.
Docs and canvas
Specs, decisions, diagrams, whiteboards, comments, versions, restores, artifact links, and workspace-scoped records.
NorthGraph
Local code intelligence for symbols, routes, effects, policies, impacted tests, verification reports, and local MCP.
CLI and MCP
Scoped tokens, JSON endpoints, context bundles, hosted VectorGraph MCP, local NorthGraph MCP, and audited agent identities.
Native integrations
GitHub-linked PRs, branches, commits, deploy evidence, and the first-party integration model for Slack, GitLab, Bitbucket, Codex, Claude, Zendesk, and Salesforce.
Execution graph
From customer signal to shipped change
VectorGraph connects product development from signal to outcome, so teams and AI agents can trace why work started, how it was built, what code shipped, and what impact it had.
In practice
One feature three roles and three walkthroughs
How an engineer, a product manager, and an executive each use VectorGraph across the same shipped change, with no copy-paste, no spreadsheets, and no standups required.
Pricing
Simple per seat pricing Start free upgrade when your team needs more control
Start on Free with your first workspace. Upgrade when you need unlimited issues, more teams, private-team access, guest access, or audit exports. Billed per user, monthly or annually, annual saves around 18% on every paid tier.
Basic
For engineering teams running day-to-day work in VectorGraph.
$9/ user · month
Billed annually at $108/user/year.
Choose Basic- Everything in Free
- Unlimited issues
- File uploads
- Up to 5 teams
- Customer requests (Signal)
Business
For larger organizations that need private teams, guest access, audit exports, and advanced controls.
$14/ user · month
Billed annually at $168/user/year.
Choose Business- Everything in Basic
- Unlimited teams
- Private teams
- Guest accounts
- Audit log export
All plans include workspace isolation, code-linked work, first-party CLI and MCP, audit trails, and workspace login. Volume pricing is available above 50 seats. Current SOC 2 status is disclosed on the security page.
Common questions answered up front
Who is VectorGraph for
Product and engineering teams shipping software with AI agents. It is for teams that want work, decisions, code context, and AI tools connected in the same workspace.
What makes VectorGraph different from other trackers
Three structural differences. First, the data model goes beyond issues: VectorGraph connects customer signal, decisions, docs, code context, pull requests, and outcomes in one workspace. Second, NorthGraph gives coding agents local, deterministic code facts where the analyzer has coverage and reports limitations where it does not. Third, agents are first-class workspace actors with their own identities and scoped capability policies, not service accounts borrowing a user’s token.
What do VectorGraph NorthGraph and vector mean
OrinTech is the company. VectorGraph is the product and platform. NorthGraph is the local code intelligence layer inside VectorGraph. The VectorGraph CLI is the command-line tool for VectorGraph and NorthGraph workflows. VectorGraph MCP is hosted workspace MCP; NorthGraph MCP is local code-intelligence MCP.
Does VectorGraph include docs and visual planning
Yes. Workspace documents and canvases are first-party, with version history, review, comments, and links back to the issues, projects, or initiatives they belong to. They are not a separate wiki your team forgets to keep updated.
What is NorthGraph
VectorGraph’s local code intelligence layer. It maps symbols, routes, side effects, tests, and project policy on a developer’s machine, then exposes that deterministic code map through local MCP so compatible agents and CI can work from the same evidence. Source code does not leave the machine by default.
Which agents and models does VectorGraph support
Any MCP-capable agent, Claude Code, Codex, Cursor, Windsurf, your in-house agent, or a local model. VectorGraph and NorthGraph are model-agnostic. You bring the agent and pay for inference where you already do.
Does VectorGraph send my code anywhere
No. NorthGraph indexes locally and stays on the developer’s machine. Workspace data lives in your tenant; the CLI and MCP surfaces operate on workspace records, not source code. There is no source-code upload by default.
How does VectorGraph keep agents inside the rules
Every agent gets its own scoped identity, with a capability policy that decides what it can read, write, and approve. CLI, MCP, and webhook calls are authenticated, authorized against the same workspace and private-team rules as a person, and written to the audit log. Agents do not have a back door the UI does not have.
How is data isolated between teams and workspaces
A workspace is the boundary. Membership is resolved server-side from the workspace in the URL on every read and write. Search, exports, notifications, real-time updates, and code-linked activity all respect it. Private teams stay private within a workspace, even from agents.
Which integrations are live or provider-ready
GitHub support is implemented for pull request, branch, and commit links. Slack, GitLab, Bitbucket, Codex, Claude, Zendesk, Salesforce, Datadog, Sentry, Resend, object storage, Neo4j, and the expanded provider catalog are provider-ready but not provider-live until credentials, install flows, webhooks, health checks, sandbox or production verification, and runbook evidence are recorded.
How much does it cost
Free is $0 with 300 issues, 2 teams, and unlimited members. Basic is $9 per user per month (annual) or $11 (monthly) for unlimited issues, file uploads, and 5 teams. Business is $14 per user per month (annual) or $17 (monthly) for unlimited teams, private teams, and guest access. Annual saves about 18% on both paid tiers.
Get started
Bring your team onto the shared work graph
Create an account, name a workspace, invite your team, connect your code, and point your agents at MCP. Start turning company context into shipped work from one shared workspace.