Architect AI
How it worksGuidesVisionPlansFAQContact
GitHubSign upSign in

Engineering memory for software teams

The code is there. The context is missing.

Architect AI helps your team understand how systems work, preserve why they were built, and onboard without relying on tribal knowledge.

Start with one repositorySee how it works

Repository-scoped answers with source references.

Open sourceSelf-hostableModel-agnosticAES-256 encrypted secrets
architect-ai / api
INDEXED

Repository map

src/auth
src/workspaces
src/repositories
src/retrieval
src/chat
1,248 symbols understood
Ask your system
How does authentication work?

Requests pass through the JWT auth guard, which verifies the access token before workspace and role guards resolve what the caller can actually do.

The memory problem

Growing codebases outlive the people who understand them.

Weeks to onboard

New engineers reconstruct the system from fragments.

Knowledge in heads

Senior engineers become the undocumented interface.

Decisions revisited

Teams lose the reasoning behind what already works.

From repository to understanding

Ask the system, not the hallway.

Architect AI turns a live codebase into a searchable, explainable context layer your whole team can use.

01

Connect

Choose a GitHub repository.

02

Understand

Parse files, symbols, and relations.

03

Ground

Build searchable repository context.

04

Answer

Stream cited answers, token by token.

cloningparsingchunkingembeddingready

Streaming answers

Tokens stream live over SSE as the model responds.

Bring your own model

OpenAI, Anthropic, Grok, or Gemini—your key, your choice.

Workspaces & roles

Owner, admin, member, and viewer access per workspace.

Encrypted at rest

GitHub tokens and API keys are AES-256-GCM encrypted.

Answer feedback

Mark answers helpful or not to track quality over time.

Model-agnostic by design

Use the model you trust.

We don't care who wins the AI wars.

Architect AI is model-agnostic. Bring your own provider, use hosted AI, or switch models whenever you want—your workspace, your call.

OpenAI

GPT models

Anthropic

Claude models

Grok

xAI models

Gemini

Google models

Hosted AI

No key required

Switch your active provider anytime from workspace settings—no redeploy, no lock-in.

Living onboarding guides

A guide for every unfamiliar system.

Every ready repository gets nine guide types—executive summary, project overview, folders, modules, services, technology stack, reading order, glossary, and pitfalls—generated automatically and regenerated on demand, all grounded in the repository and ready to ask questions from.

Generate a living guide
Guide library
v3 · READY
Executive summary
Project overview
Modules & services
Technology stack
Reading order
Glossary
Common pitfalls

Executive summary

How Architect AI fits together

A decision-oriented overview of purpose, boundaries, core flows, and open risks— grounded in the repository and ready for source-cited follow-up questions.

1Connect a repository
2Let indexing build context
3Ask your first system question

Explainable by design

Every answer has a trail back to the code.

The goal is not to replace engineering judgment. It is to give that judgment better context—scoped to the repository or workspace you are actually working in.

Repository-scoped Workspace-wide Source references
Source-grounded answerREPOSITORY: API
Which services use Redis?

Redis is used for repository indexing queues and optional retrieval caching. The indexing worker publishes jobs through BullMQ, while retrieval can cache query embeddings and assembled context.

Not another coding assistant

Coding assistants write code. Architect AI explains the system.

Copilot and Cursor answer “how do I write this faster?” Architect AI answers “how does this system work, and what happens if we change it?”

CapabilityGitHub CopilotCursorDocs toolsArchitect AI
Writes code—
Understands architecture
Preserves decisions——
Predicts change impact———
Source-cited answers—

Based on our own product research; other tools evolve quickly and may close these gaps over time.

Who it's for

Built for teams that outgrow tribal knowledge.

Early adopters

5–30 engineers, multiple repositories, growing technical complexity.

Expansion market

50–500 engineers, multiple teams, significant onboarding costs.

Enterprise

Self-hosted deployment, compliance controls, and advanced governance.

The product journey

From chat with code to engineering memory.

Start with the questions your team is already asking. Grow toward a system that remembers the reasoning behind the software.

The question this stage should answer

How does this system work?

01 / 05

Simple, honest plans

Start free. Scale when the team does.

Hosted AI is included on every plan. Bring your own model key to uncap AI questions and onboarding guides—the plan price stays the same.

BYOK uncaps AI questions and onboarding guides. Limits for repositories, indexing runs, workspace members, and indexing resource caps still follow the selected plan.

Frequently asked

Questions teams ask before connecting a repository.

Is Architect AI open source?

Yes. The full stack is open source and available on GitHub, including the API, worker, indexing pipeline, and web application.

Can we self-host it?

Yes. A Docker Compose stack runs the web app, API, worker, PostgreSQL, Redis, and Qdrant on your own infrastructure, with a documented single-host production deployment for AWS EC2.

Which AI providers are supported?

Hosted AI works out of the box. Workspaces can also bring their own key for OpenAI, Anthropic, Grok, or Gemini and switch the active provider instantly—no redeploy required.

How do plans and pricing work?

Free includes hosted AI with plan-based usage limits. PRO raises those limits for a monthly price. Enterprise is custom and starts with a conversation with sales. Connecting your own model key uncaps AI questions and onboarding guides without changing the plan price.

What happens to our source code and API keys?

Repository content is parsed and embedded to power retrieval; GitHub tokens and BYOK provider keys are encrypted at rest with AES-256-GCM and are never returned in plaintext by the API.

Which languages are supported today?

TypeScript and JavaScript are parsed today via Tree-sitter, including TSX/JSX. Additional language parsers are on the roadmap.

What is the long-term vision?

Architect AI grows from repository chat into architecture exploration, decision memory, and change-impact analysis—an engineering memory layer, not just another coding assistant.

Start with what you already have

Connect one repository. Find the answers your team keeps rediscovering.

Make the system legible before the next engineer has to learn it the hard way.

Connect a repository

Get in touch

Let's talk.

Questions about Architect AI, partnerships, or just saying hello—send a message or find me on the web.

My LandingLinkedInEmail

Architect AI · From chat with code to engineering memory

© 2026 Architect AI. All rights reserved.