Features

A basic agent receives a message, thinks, and replies. A production agent handles the messy reality of workplace chat: conversations that span days, files dropped mid-thread, long-running tasks that need visibility, and sensitive actions that need approval.

Configure each capability for your app and account for the integration limits below:

Memory

Slack conversations span hours or days. With a database configured, the agent remembers previous messages in the thread and can reference earlier context without the user restating it.

from agno.agent import Agent
from agno.db.sqlite import SqliteDb

agent = Agent(
    name="Support Bot",
    model=...,
    db=SqliteDb(db_file="sessions.db"),
    add_history_to_context=True,
    num_history_runs=5,
)

Each Slack thread maps to one session. DMs work the same way. All responses are sent as thread replies, keeping channel conversations organized. Conversations persist across server restarts.

Files

The agent can read files that users attach and generate files in response. The interface extracts attachments from incoming messages and makes them available to the agent. Generated files upload back to the thread.

from agno.tools.slack import SlackTools

agent = Agent(
    tools=[SlackTools(enable_upload_file=True, enable_download_file=True)],
)

Streaming

Responses stream live, so users see text appear as the agent generates it, with task cards showing progress on long-running work.

Slack(agent=agent, streaming=True)  # on by default

Search

The search_workspace tool calls Slack's Real-time Search API. The constructor flag below enables the tool, but the current event-token and storage limitations must be resolved before using it.

The current Slack interface copies event.assistant_thread.action_token into run metadata. It does not read the top-level event.action_token used in Slack's current agent example. Events carrying only that top-level token reach search_workspace without the required credential and return a no-token error.

Slack's Real-time Search guide prohibits retaining data retrieved by that API. Agno's ordinary session persistence can retain raw tool results; the Slack Team interface also enables member-response storage. Configure and verify event-token handling and the complete storage path before enabling this search. The workspace-tools example keeps it disabled pending those integration changes.

from agno.tools.slack import SlackTools

agent = Agent(
    tools=[SlackTools(enable_search_workspace=True)],
)

Slack selects keyword or semantic retrieval according to the query and workspace capabilities. Semantic search requires a workspace plan with Slack AI Search; check assistant.search.info for the available capabilities. See Slack's retrieval rules.

Identity

Identity resolution looks up a Slack user profile. When an email is available, Agno uses it as user_id; otherwise it retains the Slack user ID.

Slack(agent=agent, resolve_user_identity=True)

Email lookup needs users:read, users:read.email, and a successful profile response. Cross-platform memory requires your application to map identities to the same canonical user ID and share a memory store. WhatsApp phone IDs are not automatically matched to Slack email addresses, and thread sessions remain separate.

Response control

By default, the bot only responds when @mentioned in channels. In DMs, it responds to every message.

Troubleshooting

export SSL_CERT_FILE=$(python3 -c "import certifi; print(certifi.where())")

Next steps