AI and media

AI agents that use AnythingLLM

UtilitySpaces gives an AI agent scoped access to AnythingLLM through its own encrypted connection, not your password. The agent can call 4 named AnythingLLM tools, and the one that writes waits for a person's approval unless an admin has set the connection to run without asking. Every call is written to a hash-chained audit log with its arguments and its result.

What an agent can do in AnythingLLM

Query and extend an AnythingLLM instance's knowledge bases. Collections are workspace slugs. Queries run in AnythingLLM's own query mode, which answers strictly from the documents. An agent calls these by name, and matching is exact.

Every tool a AnythingLLM connection exposes, and whether it writes, which waits for approval by default
Tool	What it does	Waits for approval by default
List collections	List the knowledge bases available on this connection. Returns { collections: [{ id, name }] }.	No — read only
Query knowledge base	Retrieve the passages most relevant to a question. Returns { chunks: [{ text, score, source }], answer? }. Reads only — it never changes the knowledge base.	No — read only
Ingest text	Add a plain-text document to a knowledge base so later queries can retrieve it.	Yes — it writes
List documents	List the documents already ingested into a knowledge base.	No — read only

3 read tools, 1 write tool. Generated from the connector catalogue the product runs on, so it cannot list a tool that does not exist.

What teams hand an agent in AnythingLLM

Teams with an AnythingLLM instance hand an agent the knowledge bases: List collections shows the workspaces, Query knowledge base retrieves the passages that answer a question strictly from the documents, and List documents shows what is ingested. Ingest text is the one write, and it waits for approval unless an admin has set this connection to run without asking.

Answer policy and product questions in the channel from the knowledge base, with the source passages quoted.
Audit what a workspace actually contains by listing its documents before trusting answers from it.
Add a document -- meeting notes, a policy, a spec -- so future queries can retrieve it (after a person approves it)

Before you let it write, or keep out: Retrieval answers only from what was ingested: a stale collection produces confident answers from old documents. Think before approving Ingest text, because whatever goes in becomes tomorrow's authoritative answer.

What waits for a person

Reads run on their own. These do not — each one waits in Approvals for an owner or admin unless an admin has set this connection to run writes without asking, and every call toAnythingLLM, approved, rejected or unattended, is logged.

Ingest text POST

What connecting AnythingLLM takes

AnythingLLM uses an API key you create in AnythingLLM and paste in once. A workspace admin sets the connection up; the fields are:

Instance URL
API Key

Credentials are encrypted and bound to your workspace, never read back, and every outbound call passes one guarded fetch — the connector security posture sets out exactly how, and the security page covers the platform around it.

Where AnythingLLM fits

Give an agent AnythingLLM work by writing a message in the inbox, or put its tools in a scheduled flow. What the run cost is on the cost breakdown.

Other ai and media integrations: AssemblyAI, D-ID, Deepgram. Or see every application agents can connect to.

See it doing your actual work

Open a demo workspace, connect one app, and give an agent a real job. No card, no sales call.

Try the demo See pricing

We reply to every message within one business day.