# LlamaIndex Framework > The LlamaIndex Framework is LlamaIndex's open-source Python toolkit for retrieval and agents, with FunctionAgent, ReActAgent and CodeActAgent, multi-agent AgentWorkflow, event-driven Workflows, MCP tools and hundreds of integration packages. - Canonical: https://www.anchorterminal.com/tools/llamaindex - Pricing: https://www.anchorterminal.com/tools/llamaindex#pricing - Reviews: https://www.anchorterminal.com/tools/llamaindex#reviews - Markdown: https://www.anchorterminal.com/tools/llamaindex.md (~6,350 tokens) - Slim: https://www.anchorterminal.com/tools/llamaindex.min.md (~1,380 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/llamaindex.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT llamaindex.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade BB · 70/100 · rank #216 of 1486 · #11 in Agent frameworks & SDKs · agent-ready · confidence medium** More from LlamaIndex, listed separately because each is its own product: [LlamaParse API + MCP](https://www.anchorterminal.com/tools/llamaparse.md) (Document parsing & extraction). ## Assessment An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application. ## Facts | Field | Value | | --- | --- | | Vendor | LlamaIndex (https://developers.llamaindex.ai/python/framework/) | | Kind | Agent framework | | Category | Agent frameworks & SDKs (https://www.anchorterminal.com/categories/frameworks) | | Auth | None · A library with no credentials of its own. The default LLM and embeddings are OpenAI's and read an OpenAI key; integrations take their own keys. | | Pricing | Free (Free · OSS) · Free and open source under MIT. You pay for model calls. LlamaParse and LlamaCloud are separate paid services with their own Anchor Terminal listing. | | x402 | No · No x402, MPP or L402 in the framework docs or the repository (checked 2026-11-06). | | Licence | MIT | | Packages | pypi: `llama-index`; pypi: `llama-index-core`; pypi: `llama-index-workflows`; pypi: `llama-index-tools-mcp` | | Source | https://github.com/run-llama/llama_index | | Docs | https://developers.llamaindex.ai/python/framework/ | | llms.txt | https://developers.llamaindex.ai/llms.txt | | Last release | 2026-09-21 | | GitHub stars | 52,833 (as of 2026-11-06) | | PyPI downloads / week | 1,260,039 | | Surface listed | The LlamaIndex Framework for Python (llama-index and llama-index-core) with llama-index-workflows, read from the run-llama/llama_index and run-llama/workflows-py repositories, developers.llamaindex.ai (llms.txt, agents and MCP guides) and OSV on 6 November 2026. Nothing was installed | | Scope | The open-source framework. LlamaParse, LlamaIndex's hosted document parser, and OpenDocRouter have separate Anchor Terminal listings. A TypeScript edition exists and wasn't graded | | Agents | FunctionAgent for provider tool calling, ReActAgent and CodeActAgent for prompted tool use, and AgentWorkflow for hand-offs between agents | | Workflows | Event-driven steps with context that can be serialised and resumed, human-in-the-loop events, and a DBOS package for durable runs | | MCP | llama-index-tools-mcp loads tools from MCP servers, and workflows can be served as MCP servers | | Defaults | OpenAI for the LLM and embeddings unless Settings is changed; ChatMemoryBuffer for agent memory | | Telemetry | None found in llama-index-core. Instrumentation and callback handlers export to observability tools when configured | | Versioning | 0.14.x for core with breaking changes at minor versions such as 0.13 and 0.14; Workflows is at 2.x | | Capabilities | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | | Tags | framework, python, open-source, llms-txt, mcp, rag, workflows | | JSON | https://www.anchorterminal.com/api/v1/tools/llamaindex.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 70 | 14.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 85 | 13.8 | | Agent ergonomics | 13% | 16.2 | 73 | 11.9 | | Security & auth | 14% | 17.5 | 74 | 12.9 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 69 | 6.0 | | Transparency & trust (editorial 72, provenance 61) | 7% | 8.8 | 67 | 5.9 | | Negative events | up to −15 | up to −15 | 2025-11 to 2026-11. Advisories for llama-index-core first published in the last 12 months are GHSA-488g-hw5f-x29p (uncontrolled resource consumption, 2 February 2026, moderate, fixed in 0.12.41) and the PYSEC re-publications in 2026 of 2025 path-traversal, denial-of-service and temporary-file issues fixed by 0.13.0. Fixed and documented, so 2 points. https://osv.dev/vulnerability/GHSA-488g-hw5f-x29p | -2 | | **Total** | | | | **70 → BB** | ### Why each score - Reliability 70 (checked 2026-11-06): Local-package reading. Official PyPI packages with Python 3.10 to below 4.0 (20). Public unit-test, type-check, lint, coverage and CodeQL workflows, with the type-check, lint and CodeQL runs on main passing on 3 November (25). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). A dated, generated changelog per package, but core is 0.x and minors such as 0.13 and 0.14 carried breaking changes (8). Core isn't 1.0; Workflows is at 2.x, so partial (5). 20+25+12+8+5 = 70. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 85 (checked 2026-11-06): Framework reading. A typed Python API with a generated reference (22). llms.txt indexing the framework docs, plus a docs search API and an MCP server for the docs (10). The agents guide says what each agent class is for, and the MCP page lists the three ways to use MCP (15). Tools are typed from function signatures and Pydantic models (13). Many examples and notebooks, few documented error types (10). Dated changelog (15). 22+10+15+13+10+15 = 85. - Agent ergonomics 73 (checked 2026-11-06): Framework reading. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73. - Security & auth 74 (checked 2026-11-06): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74. - Payments & pricing 60 (checked 2026-11-06): Self-hosted rule. Free MIT packages with nothing to buy for the framework itself (20 + 20 + 20). No payment protocol (0). LlamaCloud is graded on its own listing. 0+20+20+20 = 60. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 69 (checked 2026-11-06): llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69. - Transparency & trust 67 (checked 2026-11-06): MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72. Fix list, everything this grade says the listing lacks, the biggest gain first (16 items). What it covers is at https://www.anchorterminal.com/fixes/llamaindex.md (JSON https://www.anchorterminal.com/fixes/llamaindex.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "llamaindex", "plan": "read"}`, free while the beta runs ### What we couldn't check - Reply times were sampled from comment counts on the 50 newest issues, not read issue by issue - PyPI's project pages answered a bot check, so release dates come from the repository's changelog and tags - The listing is named LlamaIndex Framework, the docs' own name, to keep it apart from the company and LlamaParse; the slug stays llamaindex ### Sources - repository (CHANGELOG, SECURITY.md, STALE.md, workflows, core source): (seen 2026-11-06) - workflows-py repository and tags: (seen 2026-11-06) - llms.txt: (seen 2026-11-06) - agents guide: (seen 2026-11-06) - MCP guide: (seen 2026-11-06) - GHSA-488g-hw5f-x29p: (seen 2026-11-06) - OSV advisories for llama-index-core: (seen 2026-11-06) - PyPI downloads: (seen 2026-11-06) - GitHub API, repository, issues and Actions runs: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/llamaindex/history.json - 2026-11-06: graded 70 BB (methodology 0.7) ## Who's behind it (provenance 61/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | LlamaIndex, Inc. | 20/20 | | Domain age | llamaindex.ai, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the MIT licence stands in | 10/10 | | Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | could not be fetched | 0/10 | | People named | 2 named with their role, none with a public profile | 7/10 | | Support route | a community | 5/5 | The framework is MIT-licensed; the company facts follow the LlamaParse listing. developers.llamaindex.ai/robots.txt allows all crawlers. The privacy policy link is the company's; the library collects nothing itself. Neither the terms nor the privacy policy was re-read for this listing. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full. **Privacy policy** (https://www.llamaindex.ai/privacy-policy), read 2026-10-08, dated 2026-08-24, states 7 of the 8 things a reader expects. - To know. Says it sells personal data or shares it for advertising. "We may share a common account identifier (such as a hashed email address or user ID) with our third-party advertising partners to help link the personal data we and our third-party partners collect to the same person, or otherwise target advertising to an individual on a third-party website or platform." - Gives the date it was last updated. Last updated 2026-08-24. - Gives a privacy contact. privacy@runllama.ai. - Not found in the text. Says where data is transferred or stored. - Also in the text (2026-10-08). Customer content, including uploaded files and documents, is used to improve the services as well as to run them. "We use this content primarily to provide you with our services, to facilitate your requests, and to improve our services." - Also in the text (2026-10-08). Business partners that receive personal data may use it for their own business and commercial purposes. "Our business partners may use your personal data for their own business and commercial purposes, including to send you information about their services." - Also in the text (2026-10-08). Disconnecting Google Drive stops further access but does not delete customer content already sent to the services. "Disconnecting Google Drive does not delete Customer Content previously provided to our services." ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Jerry Liu, Co-founder - Simon Suo, Co-founder - Note: LlamaIndex's seed announcement on its own blog, written by Jerry Liu and read 28 October 2026, says he built GPT Index, later renamed LlamaIndex, and joined forces with Simon Suo two months in to develop it. Its about and careers pages name no one in their served text, and its Series A post names no founder. Greylock's portfolio page (https://greylock.com/portfolio/llamaindex/) lists the leadership as Jerry Liu, CEO & Co-Founder, and Simon Suo, CTO & Co-Founder; as only an investor page gives those titles, the roles stay Co-founder. OpenDocRouter's site says it is made by LlamaIndex and names no person. Copied from the LlamaParse listing (checked 29 October 2026) for the LlamaIndex Framework on 6 November 2026; nothing newer was looked for. On 6 November 2026 a search for a newer round or a valuation found only databases and trackers the rules exclude; neither the seed nor the Series A post states a valuation, so none is given. - LlamaIndex: LinkedIn https://www.linkedin.com/company/91154103 X https://x.com/llama_index GitHub https://github.com/run-llama ### Ownership and investors - Raised: $27.5M in total, as of March 2025 (source https://www.llamaindex.ai/blog/announcing-our-series-a-and-llamacloud-general-availability) - Backed by: Greylock, Norwest, Jack Altman, Lenny Rachitsky, Mathilde Collin, Raquel Urtasun, Joey Gonzalez ### Getting support - Discord: https://discord.com/invite/eN6D2HQ4aX - Sources: https://www.llamaindex.ai/, https://www.llamaindex.ai/about, https://en.wikipedia.org/wiki/LlamaIndex, https://github.com/run-llama/llama_index, https://github.com/Disiok ## Live (updated 2026-11-07 16:01 UTC) - github `run-llama/llama_index` v0.14.25, released 2026-09-21 - pypi `llama-index` 0.14.25, released 2026-09-21 - pypi `llama-index-core` 0.14.25, released 2026-09-21 - pypi `llama-index-tools-mcp` 0.6.0, released 2026-08-31 - pypi `llama-index-workflows` 2.26.1, released 2026-10-21 - security.txt: none - Watching changelog - Watching privacy , last changed 2026-11-06 13:51 UTC - Always current: https://www.anchorterminal.com/api/v1/live/llamaindex.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - FunctionAgent, ReActAgent, CodeActAgent and multi-agent AgentWorkflow over one Workflows engine - Workflow context serialises and resumes, with a DBOS package for durable runs - Hundreds of integration packages for models, vector stores and data loaders - No telemetry found in llama-index-core - huntr bug bounty and public advisories with fixed versions ## Weaknesses - Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes - OpenAI is the default LLM and embedding provider unless Settings is changed - No per-tool approval primitive; the threat model leaves input validation to the application - Several 2025 path-traversal and denial-of-service advisories in core and readers ## Before you call it (notes for agents) 1. Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default 2. Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs 3. Use Workflow human-in-the-loop events before tools that write or send 4. Pin llama-index-core to a minor version, since minors have broken APIs 5. Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories ## Get started Install: ```bash pip install llama-index # MCP tools: pip install llama-index-tools-mcp ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | AI SDK | AA | 89.8 | 1 | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | no | https://www.anchorterminal.com/tools/vercel-ai-sdk.md | | OpenAI Agents SDK | AA | 86.2 | 3 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/openai-agents-sdk.md | | Pydantic AI | A | 81.9 | 7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/pydantic-ai.md | | Strands Agents | A | 80 | 15 | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | no | https://www.anchorterminal.com/tools/strands-agents.md | | Microsoft Agent Framework | A | 79.4 | 18 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/microsoft-agent-framework.md | | Mastra | BB | 74.2 | 91 | agent.framework, agent.durable, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/mastra.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - llama-index-core 0.14.25 is the newest core release, in the changelog entry of 21 September 2026; the previous one was 19 August, while integration packages publish separately (source: ) - Workflows live in run-llama/workflows-py as llama-index-workflows, 2.26.1 on 21 October 2026, beside the llama-agents server and DBOS durability packages (source: ) - SECURITY.md runs a bug bounty on huntr for llama-index, llama-index-core, the OpenAI integrations and llama-index-cli, and its threat model puts input validation on the hosting application (source: ) - OSV lists path-traversal, denial-of-service, temporary-file and pickle-serialiser advisories for llama-index-core first published between July and September 2025, all fixed by 0.13.0, and one more (GHSA-488g-hw5f-x29p) on 2 February 2026, fixed in 0.12.41 (source: ) - Earliest tag in the repository is v0.2.17 of 28 January 2023 (source: ) - #11 of 20 in Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md - All 171 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md ## Compare - [AgentOS vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agentos-vs-llamaindex.md): BB 75.8 vs BB 70 - [Agno vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agno-vs-llamaindex.md): BB 70.9 vs BB 70 - [BoxLang AI vs LlamaIndex Framework](https://www.anchorterminal.com/compare/boxlang-ai-vs-llamaindex.md): B 65.8 vs BB 70 - [Claude Agent SDK vs LlamaIndex Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.md): BB 70.3 vs BB 70 - [CrewAI vs LlamaIndex Framework](https://www.anchorterminal.com/compare/crewai-vs-llamaindex.md): C 59 vs BB 70 - [Cursor Agent SDK vs LlamaIndex Framework](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex.md): B 63.7 vs BB 70 - [Docker Agent vs LlamaIndex Framework](https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex.md): BB 73.6 vs BB 70 - [Agent Development Kit (ADK) vs LlamaIndex Framework](https://www.anchorterminal.com/compare/google-adk-vs-llamaindex.md): B 68.7 vs BB 70 - [guilds.run vs LlamaIndex Framework](https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex.md): D 53.4 vs BB 70 - [LangGraph vs LlamaIndex Framework](https://www.anchorterminal.com/compare/langgraph-vs-llamaindex.md): B 69.8 vs BB 70 - [LlamaIndex Framework vs Mastra](https://www.anchorterminal.com/compare/llamaindex-vs-mastra.md): BB 70 vs BB 74.2 - [LlamaIndex Framework vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.md): BB 70 vs A 79.4 - [LlamaIndex Framework vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk.md): BB 70 vs AA 86.2 - [LlamaIndex Framework vs Pydantic AI](https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai.md): BB 70 vs A 81.9 - [LlamaIndex Framework vs smolagents](https://www.anchorterminal.com/compare/llamaindex-vs-smolagents.md): BB 70 vs C 58.7 - [LlamaIndex Framework vs Strands Agents](https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.md): BB 70 vs A 80 - [LlamaIndex Framework vs TradingAgents](https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents.md): BB 70 vs C 61.4 - [LlamaIndex Framework vs AI SDK](https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk.md): BB 70 vs AA 89.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on llamaindex.ai or one of its subdomains, or the README at the root of github.com/run-llama/llama_index. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "llamaindex", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html LlamaIndex Framework on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![LlamaIndex Framework on Anchor Terminal](https://www.anchorterminal.com/badges/llamaindex.svg)](https://www.anchorterminal.com/tools/llamaindex) ``` Plain link: ```html LlamaIndex Framework on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say LlamaIndex Framework is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/llamaindex-dark.png - Light: https://www.anchorterminal.com/assets/share/llamaindex-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp