Scout: Company Intelligence Agent

Scout is an open-source company intelligence agent. It navigates live information sources (web, slack, drive, wiki, CRM, MCP servers) to assemble context on demand - and builds its own wiki and CRM as it learns about your company.

YC's Summer 2026 RFS named "Company Brain" and "AI Operating System for Companies" — the same idea from two angles: pull knowledge out of fragmented sources and turn it into something AI can act on. The brain is the data layer. The OS runs on top of it. Neither exists as a finished product today, but the pieces do.

Scout stitches them together using patterns that already work: navigation over search, context providers, agentic SQL, and persistent memory.

Navigation over search. The default move when working with knowledge sources is to ingest everything into a vector db, chunk, embed, and pray. There are many reasons this doesn't work. Coding agents figured out the right approach. They navigate: ls, grep, open the file, follow the import. Scout does the same thing across Slack, Drive, and the rest.

Scout maintains its own wiki and CRM. Most information Scout learns from working with you is perfect for a wiki and CRM. "Josh from Anthropic shared a new RLM paper". Scout adds Josh to the CRM, parses the paper into the wiki, and links them.

Quick start

Prerequisite: Docker Desktop installed and running (install guide).

git clone https://github.com/agno-agi/scout && cd scout

cp example.env .env
# set OPENAI_API_KEY in .env

docker compose up -d --build

Scout is now running at http://localhost:8000.

Chat with Scout

1. Open os.agno.com and log in.
2. Click Add OS, choose Local, enter http://localhost:8000, then Connect.
3. Try the pre-configured prompts.

https://github.com/user-attachments/assets/ed49a6c4-926b-4d5d-a105-8a0d15021d3b

Chat with Scout in Slack

Scout is designed to live in Slack as your teammate. Follow docs/SLACK_CONNECT.md to add Scout to your slack workspace.

https://github.com/user-attachments/assets/69d1c409-ff94-4c8e-b5e8-64c6e1a0518a

How Scout works

Scout is a single agent with multiple context providers. Each context provider exposes 2 natural-language tools to interact with an information source:

• query_<source>: reads
• update_<source>: writes (when supported)

This thin layer solves three problems that hit any agent with a diverse tool surface: context pollution from too many tools, degrading performance from overlapping scopes, and the main agent forgetting its job because its context is all tool quirks.

The win is that a sub-agent behind each provider owns the source's quirks. Scout sees query_slack. Behind it, a sub-agent knows to look up the user before DMing, paginate by cursor, and prefer conversations.replies for threads. Scout's context never sees any of that.

"Find the latest benchmark numbers for model X." → query_web, cites sources.

"Save that as a note." → update_crm → write sub-agent INSERTs into scout.scout_notes.

"File a runbook for incident response." → update_knowledge → wiki sub-agent writes a markdown page under wiki/knowledge/runbooks/.

"Track my coffee consumption: flat white, extra shot." → update_crm → write sub-agent creates scout.scout_coffee_orders and inserts the row. Schema on demand.

"Draft a Slack message announcing the launch." → query_voice first to load the style guide, then drafts in that voice.

Context Providers

A ContextProvider exposes an information source to the agent.