LlamaIndex

Agents execute tools defined as Python functions or FunctionTool and QueryEngineTool classes, plus pre-defined Tool Specs for common APIs, and the docs cover MCP and data connectors, so tools can be written by the customer or taken from a catalog.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/deploying/agentsread 2026-09-21

Workflows stitch Parse, Extract, Split, Classify and custom Python operations into event-driven multi-step processes, with multi-agent patterns in the framework and a durable runtime that releases idle workflows and resumes them, so one process can mix deterministic operations with agent steps.

SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/overview and /python/llamaagents/workflows/dbosread 2026-09-21

The framework's ingestion pipeline loads content through data connectors into documents and nodes, builds persistent indexes over vector stores, and queries them through retrievers and query engines, which is a maintained retrieval structure over the customer's own content; extraction adds citations and confidence scores.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/indexing and llamaindex.ai/pricingread 2026-09-21

Workflows pause on a built-in InputRequiredEvent that tells the caller what is needed, such as approving a draft, and resume only when a HumanResponseEvent comes back, with deployed workflows accepting that response over a documented events endpoint and a human-in-the-loop starter template; that is the vendor's own pause-and-approve mechanism at the workflow step.

SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/workflows/human_in_the_loop and /workflows/deploymentread 2026-09-21

LlamaIndex states it is certified for SOC 2 Type II, GDPR and HIPAA, with custom BAAs and a trust center hosted on Vanta at security.llamaindex.ai, and Enterprise adds SSO and MFA for the customer's own identity provider.

SourceLlamaIndex, llamaindex.ai/pricing and security.llamaindex.airead 2026-09-21

LlamaIndex's own instrumentation and OpenTelemetry integration capture LLM calls, agent steps, retrieval components and workflow steps as spans exported to a backend the customer runs, and deployed workflows show an events log, so each step can be inspected. The trace store is the customer's chosen backend, and no audit log separate from runtime traces and no retention by plan is documented.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/observability and /python/llamaagents/workflows/observabilityread 2026-09-21

The Memory class holds short-term memory as a token-limited queue of messages scoped by session, and long-term memory blocks that receive messages flushed from short-term memory and extract information over time, merged back into context on retrieval with a stated priority when limits are hit, so both the scope and the lifetime of memory are stated.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/deploying/agents/memoryread 2026-09-21

The platform is offered in US and European regions, and Enterprise adds SaaS or hybrid deployment, private VPCs across cloud providers so data never leaves the customer's tenant, and documented self-hosting and bring-your-own-cloud deployment; the open source framework runs wherever the customer runs it.

SourceLlamaIndex, llamaindex.ai/pricing and developers.llamaindex.ai/llamaparse/self_hostingread 2026-09-21

LlamaAgents offers starter templates deployable in one click from LlamaCloud, each a complete, working document workflow application, including SEC Insights for classifying financial filings and extracting insights and Invoice Matching, and each one does its own job without the others.

SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/cloud/click-to-deploy and llamaindex.ai/pricingread 2026-09-21

Deployed workflows start on documented HTTP calls and accept events while running, so any outside system can be wired to them, but every source is wired up by the customer rather than built in as a channel, and no schedule or event subscription that wakes an agent on its own is documented; the platform's webhooks are callbacks on finished jobs.

SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/workflows/deployment and llamaindex.ai/pricingread 2026-09-21

The developer chooses the LLM and embedding model from the framework's model integrations, and agents send tool schemas to whichever provider is configured, so model choice sits with the customer.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/models and /module_guides/deploying/agentsread 2026-09-21

The LlamaParse Platform ships an SDK and API key access to Parse, Extract, Classify, Split and Index, deployed workflows expose documented HTTP endpoints, and the framework itself is a Python and TypeScript SDK, so outside callers drive the platform.

SourceLlamaIndex, developers.llamaindex.ai/llamaparse and /python/llamaagents/workflows/deploymentread 2026-09-21

The evaluation module scores the customer's own pipeline: a faithfulness evaluator checks whether answers are supported by the retrieved context, a retriever evaluator scores retrieval against named metrics, and a batch runner evaluates sets of queries as scored test cases.

SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/evaluatingread 2026-09-21

Parsing documents is not operating an interface, and no browser, desktop or computer control is documented for the framework, LlamaAgents or the LlamaParse Platform.

SourceLlamaIndex, developers.llamaindex.airead 2026-09-21