Skip to main content
Installation

Requirements

Splunk versions, the two packages, LLM endpoints, outbound network, browsers.

Splunk

ItemRequirementNotes
VersionSplunk Enterprise 10.0+The requests engine runs on every version
Agentic engine10.2+, Python 3.13The official splunklib.ai Agent exists only on this combination; anything older falls back to the requests engine and the AI settings page states why (python_too_old / splunklib_ai_missing)
KV storeEnabledConversations, knowledge base, triage results, asset tables, reports and preferences all live there
TopologySingle search head or search-head clusterInstalls on the search head; nothing on indexers
Enterprise SecurityOptionalWith ES, live alerts read index=notable and verdicts write back to the notable; without ES the alert source can be any index
Splunk Cloudfallback packageThe fallback package (pure Python, no binaries) is the one that passes AppInspect Cloud; the selfcontained package carries a compiled trust anchor and cp313 wheels and is for on-prem only

The two packages

PackageContentsWhere
rst_splunk_ai_copilot-<version>-fallback.splPure Python, requests engineSplunkbase, Splunk Cloud
rst_splunk_ai_copilot-<version>-selfcontained.splsplunklib.ai and dependencies bundled (~120 MB of cp313 wheels), licence trust anchor compiled to .soOn-prem Splunk Enterprise 10.2+

Both packages have the same features. The difference is the agentic engine: it lets the model call read-only tools to probe the real schema, dry-run its SPL and gather evidence around an alert. The requests engine answers the same prompts in one turn without probing.

A 10.2+ host running the fallback package can later run scripts/vendor_agentic.sh on the search head to install the stack into bin/lib/, which is equivalent to the selfcontained package.

LLM

Any OpenAI-compatible chat-completions endpoint. Verified: Volcengine Ark coding plan (ark-code-latest, doubao-seed-*, kimi-k2.7-code, deepseek-v4-*, glm-5.3), DeepSeek, Alibaba DashScope, OpenAI, OpenRouter, local Ollama / vLLM.

  • At least a 32k context; investigation and triage prompts carry evidence and a short context truncates them.
  • Function calling is not required; the agentic engine uses splunklib.ai's own protocol.
  • Semantic retrieval (optional) needs a separate embeddings endpoint. It is off by default and the knowledge base falls back to keyword retrieval.

Network

DirectionTargetPurpose
OutboundLLM endpoint :443Every AI call
Outboundlicense.reallysec.com :443Online activation, heartbeat, revocation list; not needed with an offline licence
Outbound (optional)Threat-intel vendor, ServiceNow / Jira, Feishu / DingTalk / WeCom / Slack / Teams / SMTP, syslog / webhookEach egresses only once enabled in copilot.conf or in the UI; all off or unconfigured by default
InboundNoneEverything goes through Splunk Web on 8000

The MCP server (1.9.0+) listens on 127.0.0.1:18100 by default; other machines need a TLS reverse proxy in front.

Browser

The last two major versions of Chrome / Edge / Firefox / Safari. The UI is laid out for 1280 px and wider; below 1024 px the sidebar collapses.

On this page