Skip to content

> cat /etc/evolution.log

What Maguyva runs on

Built for speed, debuggability, and continuous improvement: proven infrastructure at the core, purpose-built components where code intelligence requires them.

PostgreSQL + LanceQuantized vector searchCode language engineMCP everywhere279+ languages

> lsmod | grep production

What runs in production

These are the core layers that stayed after multiple iterations. Every one of them earned its place by making debugging easier or by removing friction from agent execution.

Database

PostgreSQL + Lance

Tenant-partitioned storage and indexes. Your code stays isolated, with no cross-user index mixing.

Embeddings

Voyage AI: voyage-4-large

High-recall code embeddings for agent search, retrieval, and grounding.

Vector Search

Binary Quantized HNSW

Embeddings compressed to 2048-bit signatures and indexed with HNSW. 32x storage reduction, low-latency search, zero extra infrastructure.

Language Engine

Code Language Engine

A heavily modified Tree-sitter stack with custom grammars, handler heuristics, and 279-language extraction coverage

Protocol

MCP Protocol

Remote MCP server for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, and other MCP-compatible clients. 11 tools on a TypeScript Cloudflare Worker with native streamable HTTP transport.

Cache

Lance columnar + R2

Columnar-cached, cloud-synced embeddings

Architecture Timeline

The stack after the dead ends

Maguyva did not arrive at this shape all at once. Each layer survived because it made the system faster to reason about, cheaper to operate, or easier to debug under pressure.

The orchestration experiments started earlier. This timeline starts in September 2025, when the Maguyva product itself snapped into focus.

1
2025-Q3foundation

Focused Maguyva build starts → Voyage voyage-code-3

The product direction hardens and the rapid iteration loop begins

2
2025-Q3storage

Binary vector retrieval layer

Quantized search with compact indexes, no separate vector stack

3
2025-Q4ast-engine

Code language engine comes online

Custom queries, parser fallbacks, and handler-based heuristics across 279 languages

4
2025-Q4search

Multi-modal fusion search

Ranked retrieval across semantic, text, AST, and graph indexes in a single query

5
2026-Q1caching

Lance columnar + R2 sync

Server-side columnar cache, faster cold starts

6
2026-Q1quality

279-language validation framework

Automated extraction testing across every supported language

7
2026-Q1launch

Public launch at maguyva.ai

7 months from focused build to public availability

8
2026-Q2protocol

TypeScript Cloudflare Worker MCP

Native streamable HTTP transport, lower latency, swapped under live traffic

NOWembeddings

Production embeddings → voyage-4-large

Higher-recall semantic search after cutover from voyage-code-3

> ps aux | grep maguyva

We run on what we ship

Maguyva is built by agents that run on Maguyva.

Our orchestration system coordinates specialist AI agents that use the same MCP tools, search indexes, and production infrastructure you get. There is no internal version. The team page lists “1x Maguyva ($149) — we pay ourselves.” That is not a joke. It is the invoice.

// customer zero ships to production daily

> cat /etc/principles.d/*.conf

The rules that survived production

These are the constraints that stayed useful in production. They are less about ideology and more about keeping the system understandable while agents are making changes at speed.

!

No Silent Fallbacks

Fail fast, fix fast. Every error surfaces immediately. No graceful degradation hiding bugs in production.

// panic > silent corruption

λ

RPC-First

Database-side logic for performance. PostgreSQL functions execute close to data, eliminating round trips.

// PostgreSQL functions, 0 ORMs

CQRS

Separate write and read paths. Indexing pipeline writes, MCP tools read. Different optimization strategies.

// writes: batched | reads: cached

#

Deterministic UUIDs

Cache coherence without database lookups. Same input = same ID. Idempotent operations by design.

// uuid5(namespace, content_hash)

The best architecture is the one you can debug at 3am.
(We've tested this.)

// last updated: 2026-07

Try it on your repo

> ssh infra@maguyva -- status

Where your code lives

No mystery. Here's exactly what happens to your code when you connect a repo.

Compute

Metal servers, US East

Bare-metal machines in Ashburn, tuned for indexing throughput instead of noisy general-purpose instances.

Edge

Cloudflare global CDN

API and MCP responses cached at the edge. Static assets served from Cloudflare's global network.

Isolation

Tenant-partitioned per workspace

Each workspace gets tenant-scoped repository indexes across the pipeline and database. We use customer code to provide code intelligence, not to train models or sell data.

Entity

Singapore incorporated

UT International PTE. LTD. Real jurisdiction, real entity.

Deletion

Remove a repo, remove the index

Disconnect a repo and Maguyva removes active indexed source code, embeddings, and graph data from the service. Residual backups expire on the retention schedule.

Regions

Need EU or AU?

Additional deployment regions are a conversation for customers with residency requirements.