Claude Agent SDK vs LlamaIndex Framework

Claude Agent SDK 95

The documented agent with one MCP server is about 15 lines with the built-in client, and tool search, the default, withholds MCP tool definitions, both re-read on the MCP page on 1 November (25). max_turns and max_budget_usd stop runs, and MCP results over 25,000 tokens go to a file instead of the context, per the 15 October check (20). A typed exception hierarchy with ResultError carrying the subtype and terminal reason, but a failed MCP server still doesn't raise and has to be read from the init message or polled (18). Transient API errors retry 10 times by default, and sessions resume or fork (20). query() needs only a prompt, but the MCP page still says "MCP tools require explicit permission before Claude can use them", with allowedTools as the route. Since Claude Code 2.1.302, which Python 0.2.176 and TypeScript 0.3.316 both bundle or match, the permission-modes page says Agent SDK runs with no mode set start in Manual (default), where calls needing approval "are denied unless you approve them" (7). Python and TypeScript (5). 25+20+18+20+7+5 = 95. Judgement call. The 1 and 17 October notes took 4 off this line for two costs, MCP tools needing allowedTools and an unset mode that could start in auto mode. The second has gone. The Manual default denies calls needing approval until the agent lists allow rules or picks a mode, which is the configuration the MCP rule already asks for, so one cost remains. Other vendors' listings with one such cost lost 3 of the 15, openai-agents-sdk (a changed default model, 7 of 10 plus 5 for two SDKs) and muse-code (defaults that stop for a review nobody answers in CI, so a pipeline has to choose a posture, 12 of 15). We took that reading. Keeping 6 would count one cost twice, and the lighter reading gives 8.

LlamaIndex Framework 73

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.

Claude Agent SDK 40

No payment protocol (0). Claude model prices and Managed Agents at $0.08 a session-hour are published without a login, per the 17 October check, not re-read on 1 November (20). The package is free and needs no card (20). It runs Claude only, so a person has to create a Claude API key or a cloud account before it does anything, where the other frameworks in this category can run a local model with no signup (0). 0+20+20+0 = 40. Judgement call, and it goes against Anthropic's own listing. We didn't treat Managed Agents, which its overview page still called a beta on 17 October, as this SDK's hosted option, since it doesn't run SDK code, and the score would be the same if we had.

LlamaIndex Framework 60

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.

Claude Agent SDK 87

Python 0.2.176 and TypeScript 0.3.316, both tagged on 31 October, PyPI and npm unreadable from here on 1 November (30). 47 Python release tags (0.2.129 to 0.2.176) and 81 TypeScript tags (0.3.221 to 0.3.316) between 4 August and 31 October, inside the 90 days from 3 August (20). Recent bug reports carry triage labels (bug, regression, invalid), but 185 open issues and about 260 open pull requests is a large backlog, and we couldn't see reply times. Per the 1 October check, not re-read on 1 November (15). Python and TypeScript packages both current, each bundling or matching Claude Code 2.1.316 (15). CI and a dependency-graph workflow pass per the 1 October check. Releases have run without a gap since 6 October, 0.2.165 added an alert for blocked releases, 0.2.169 hash-pinned the build tools and 0.2.170 moved to trusted publishing, but no Python release shipped from 30 September to 6 October, and earlier yanks and the partial publish in #1234 still stand (7). 30+20+15+15+7 = 87.

LlamaIndex Framework 69

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.

Claude Agent SDK 83

The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package's LICENSE.md still says All rights reserved under Anthropic's Commercial Terms, both re-read in the clones on 1 November (18). The data-usage page, re-read on 1 November, states 30-day retention for commercial and API users, zero data retention for qualified accounts, no training on commercial data and 30 days of local transcripts in ~/.claude/projects, but still names the logging and error-tracking services only as third parties (25). Deprecations appear in the changelogs without dates, and there's no written deprecation policy for the SDK (8). Telemetry is documented per provider, with an opt-out for each service (20). 18+25+8+20 = 71. Judgement call on the licence line, written on Claude.

LlamaIndex Framework 67

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.

Claude Agent SDK 83

Usage metrics go to Anthropic and third-party logging by default on the Claude API, without code, prompts or file paths, and DISABLE_TELEMETRY=1 turns them off. They're off by default on Google Cloud, Bedrock, Foundry and Claude Platform on AWS, unless a host platform sets CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST. WebFetch sends hostnames to api.anthropic.com for a blocklist check on every provider, with its own opt-out. All re-read on the data-usage page on 1 November (20). canUseTool approval callback and PreToolUse hooks, plan and dontAsk modes with deny rules, and sandbox settings for shell commands, re-read on the permissions page on 1 November. TypeScript 0.3.301 added per-tool always_ask and always_deny policies for in-process MCP servers, and 0.3.314 and 0.3.316 typed blockWritesOutsideWorkingDirectories and blockReadsExemptPaths (20). Hooks can block a call and auto mode runs a classifier on actions, but there's no input or output guardrail primitive (10). OpenTelemetry export to your own collector stays off until CLAUDE_CODE_ENABLE_TELEMETRY=1 is set, prompt and tool content need separate flags, and tool_decision and permission_mode_changed events can form a per-user audit trail, per the observability page read on 15 October (15). HackerOne bug bounty, advisories published on the claude-code repository, whose SECURITY.md is unchanged in the clone, and anthropic.com's security.txt valid to 31 December 2026, re-read on 1 November, but neither the Python nor the TypeScript SDK repository has a SECURITY.md, checked again in both clones on 1 November (18). 20+20+10+15+18 = 83. Framework reading, so SOC 2 isn't scored, as for claude-code. The bundled CLI's advisories are counted under negative events, not here.

LlamaIndex Framework 74

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.