# LlamaIndex

Data framework for connecting LLMs to external data with RAG, agents, and structured retrieval.

## Agent Decision Summary
- Risk level: moderate
- Source confidence: medium
- Recommended workflows: Memory or RAG workflow
- Permission surface: memory, external services
- Agent JSON: https://www.openagent.bot/agents/llamaindex.agent.json

## What It Does
LlamaIndex is a agent in the agents category. Data framework for connecting LLMs to external data with RAG, agents, and structured retrieval.

## How To Evaluate
Evaluate LlamaIndex by starting from the official sources, checking its interface surface, and running one narrow workflow before expanding scope.


## Fit Matrix
- Memory or RAG workflow: strong. LlamaIndex has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Coding agent workflow: partial. LlamaIndex has at least one signal for coding agent workflow, but should be checked against a real task before adoption. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: partial. LlamaIndex has at least one signal for connector or protocol layer, but should be checked against a real task before adoption. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Evaluation and observability: partial. LlamaIndex has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. LlamaIndex has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Browser automation: weak. LlamaIndex is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.

## Evidence
- verified: LlamaIndex is listed as open source. Source: License metadata: MIT
- verified: LlamaIndex has a recorded GitHub repository: run-llama/llama_index. Source: Resource facts and GitHub source link.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/run-llama/llama_index

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: MIT
- Last verified: 2026-06-16
- GitHub repo: run-llama/llama_index
- GitHub stars: 46000

## Links
- GitHub: https://github.com/run-llama/llama_index

## Structured Outputs
- JSON: https://www.openagent.bot/agents/llamaindex.json
- Markdown: https://www.openagent.bot/agents/llamaindex.md
- Agent JSON: https://www.openagent.bot/agents/llamaindex.agent.json
- Canonical: https://www.openagent.bot/agents/llamaindex