A local AI coding assistant.
ContextMint decides what ships.

Ask, Plan, and Agent on your machine, with evidence and human approval before anything writes. Coming soon.

AI CODING ASSISTANT · DECISION-CONTROL PLANE · COMING SOON

Solo developer, or a team

One product. A solo developer starts frictionless on one machine and can turn on controlled checks. A small company or enterprise adds a shared server, SSO, and an admin lock so the team cannot change posture or cloud.

Frictionless by default
Solo developer

Install Engine and the VS Code extension. The default is frictionless. Turn on controlled checks when you want evidence review and patch approval. No signup, shared server, or SSO.

  • Ask how the codebase fits together, plan the change, and let Agent propose it
  • Frictionless by default; controlled when you turn on evidence review and patch approval
  • Optional bring-your-own-key cloud, off until you turn it on
  • Code and the index stay on your machine

Getting started

Everything in solo, plus
Small company / enterprise

Everything in the solo path. An admin can lock posture and cloud so a developer cannot change them.

  • Shared on-prem server for the team
  • SSO and workspace roles
  • Admin lock for frictionless or controlled, and for bring-your-own-key cloud
  • Quality map and operator audit for the team

Talk to us

On a coding day

Coming soon. Ask how the repo fits together and plan a change across the files it touches. Frictionless by default. Turn on approval when you want the patch to wait.

Ask, Plan, Agent

Explain the repo, write a plan for the change, or propose the patch. Approval waits for you when controlled checks are on.

Change scope

Work spans the files a change touches, with citations from the indexed workspace.

Review the change

Review a file, branch, feature, or flow, then decide what to accept.

Context Lens

See the retrieved evidence and the chosen model before the assistant answers.

Default: local Engine + Ollama per developer. What it does → Shared on-prem API server path for regulated pilots — deployment models. Optional BYOK cloud routing is off by default. Roadmap: v1.0 (coming soon) · v2.0 Engineering Intelligence · Track B enterprise & compliance. Full roadmap → · Verification Engine vision → · Getting started →

Your machine, your coding session

ContextMint Engine is a tray-native operator console — like Ollama or Docker Desktop, not a SaaS dashboard. It follows your OS theme, shows readiness at a glance, and stays out of the way until you need to start, stop, or diagnose. ContextMint is where engineers work. Click any screenshot to enlarge.

Operator console Every tab at a glance — overview, server, models, indexing, and more. Tray-first the rest of the time.
Work surface Readiness → compose → chat → inspector → patch preview. Ask, Plan, and Agent in the editor.
Human gate Summary strip, retrieved evidence, and governance notes before the model runs.

Getting started guide What it does

Code Ask, Plan, and Agent in VS Code
Evidence Context Lens before the model answers
Approval Patch preview before anything writes

The Problem Isn't Code Generation. It's Trust.

AI creates changes faster than organizations can review them with evidence. That is a board-level risk — not a tooling gap.

AI Creates
Changes faster than humans can reason about them
Reality is Fragmented
Ownership, intent, and policy live in different tools
Result
Risky merges and ungoverned agent output

The Bottleneck Moved

Code generation is no longer the constraint. Evidence and human oversight are.

Before AI

Humans generated code slower than organizations could review it.

Bottleneck: Code Generation
After AI

AI generates code faster than organizations can verify with evidence.

Bottleneck: Evidence & Governance

A coding assistant with a record

Ask, Plan, and Agent use the indexed workspace. Context Lens shows the evidence. Patch preview waits for your approval — on your machine, or on a shared server for a team.

Coding assistant | Scenario: assisted change in VS Code
Checks before the model answers or applies
✓ Context Lens — retrieved chunks, scores, routing
✓ Quality map — stored findings (duplicates, structure)
✓ Citations — answers grounded in indexed excerpts
⚠ High-severity apply — blocked until human review
✓ Patch preview — unified diff before anything writes
Recommendation
HUMAN APPROVAL REQUIRED
Traceable Evidence
✓ Context Lens chunks
✓ Findings Store finding IDs
✓ Patch preview unified diff
✓ Routing badge local model path
Coding-assistant example: Context Lens, quality map, citations, apply gate, and patch preview with human approval and cited evidence.

Roadmap PR verification gates, blast-radius, and CI packaging are the Verification Engine direction — after the coding assistant.

Why CI Tools Don't Solve This Alone

Linting and tests catch syntax. They don't give developers evidence gates in the IDE.

GitHub / GitLab
Code & PRs
No pre-inference evidence review in the IDE
SonarQube / SAST
Syntax & CVEs
No human apply gate for assisted edits
Jira / Confluence
Plans & docs
Disconnected from indexed workspace evidence
ContextMint
Local AI coding assistant — Ask, Plan, Agent, Context Lens, patch preview

Start coding locally. Add team control when you need it.

A solo developer installs Engine and the extension and starts in VS Code.
A small company or enterprise adds a shared server, SSO, and human approval.