Trust your agents, see what they see How Dosu compares to Unblocked

Go beyond context retrieval to full-context lifecycle with Dosu.

Self-learning knowledge cache tailored for you and your agents

Dosu improves coding-agent performance by drawing on a knowledge layer that keeps learning. No re-reading the entire codebase on every task — your agents get exactly the context they need, when they need it.

# eng-help

MiguelTuesday at 4:43 PM

@Dosu what GCP service backs our code retrieval tools?

DosuAPPTuesday at 4:43 PM

Cloud Filestore (NFS) — a 2.5 TB BASIC_SSD instance mounted at /mnt/filestore. It stores LanceDB vector databases that power code search and retrieval. The internal-api mounts it read-write for indexing, and the search-api mounts it read-only for queries [1].

The search-api Cloud Run service sits in front of it, handling vector and full-text search requests from agents over a direct VPC network interface for low-latency access.

111

DonnieToday at 10:27 AM

@Dosu can u update our docs with this?

DosuAPPToday at 10:27 AM

Updated! I've added the Cloud Filestore / LanceDB architecture details to the infrastructure docs. Let me know if anything needs adjusting.

Code Retrieval Infrastructure

Notion

Synced

Engineering / Infrastructure / Code Retrieval Infrastructure

Code Retrieval Infrastructure

Last edited 4 min ago

GCPSearchProduction

Our code search and retrieval pipeline is backed by Cloud Filestore (NFS) — a 2.5 TB BASIC_SSD instance mounted at /mnt/filestore. It stores LanceDB vector databases that power all vector and full-text search across the codebase.

Source: This page was reconciled from a thread in #eng-help started by Miguel on Tuesday at 4:43 PM.

Filestore configuration

Property	Value
Instance type	BASIC_SSD
Capacity	2.5 TB
Mount path	/mnt/filestore
Protocol	NFS
Network access	Direct VPC (low latency)

Answers are where it starts, not where it ends

An answer in a chat window helps the one person who asked. It cannot be reviewed, corrected, versioned, or handed to the next engineer — and it is gone by the next sprint.

Dosu turns those moments into discrete documents that live in the tools you already use, get reconciled on every pull request, and carry a link back to the thread they came from. You manage a knowledge base, end-to-end — not a stream of one-off replies.

Knowledge your agents learn from and write back to

Retrieval is a one-way street: it reads what already exists and hands it to whoever asked. Whatever an agent works out along the way stays in that one session and disappears with it.

Dosu closes the loop. What gets learned is written back to the source it came from — across code repos, docs, and team communication tools — so the knowledge layer compounds instead of fragmenting into conflicting copies.

AI-native knowledge for AI-native engineers and agents

Dosu generates and maintains the structured context that coding agents actually consume and collaborate on — reconciled on every pull request, served over MCP and the CLI, shared across your whole team.