Write a review

Head to head · Agent frameworks · October 2026 research run

Claude Agent SDK vs guilds.run

Claude Agent SDK scores 72.1 (BB) on agent readiness against guilds.run's 56.5 (C), and leads in 6 of 7 scored categories. guilds.run leads on payments & pricing. Both do agent frameworks.

Best agent frameworks and SDKs · All 55 frameworks comparisons

Claude Agent SDKAnthropic · Agent framework BB72.1/100#115 of 1084 guilds.runCigale AI · Agent framework C56.5/100#674 of 1084

Which one, for what

Claude Agent SDK BB

Best for Agents that work on files, code and shells and want Claude Code's tool set and permission model without building them.

Ahead on

  • Reliability, 70 against 53
  • Schema & documentation, 89 against 58
  • Agent ergonomics, 94 against 67
  • Security & auth, 83 against 68
  • Maintenance & community, 87 against 41
  • Transparency & trust, 83 against 52

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

Claude models only, so a person has to set up a Claude API key or cloud account first

guilds.run C

Best for A person or small team that wants a standing, inspectable team of agents with schedules, shared tables and a web app, run on one machine, and is comfortable tracking main.

Ahead on

  • Payments & pricing, 60 against 40

Also in its favour

  • Free to start without a card
  • Open source

Watch for

No tagged release, version number, changelog or published image. Users install whatever is on main

Score by category

CategoryWeight this runClaude Agent SDKguilds.runEdge
Reliability16%207053Claude Agent SDK +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28958Claude Agent SDK +31
Agent ergonomics13%16.29467Claude Agent SDK +27
Security & auth14%17.58368Claude Agent SDK +15
Payments & pricing10%12.54060guilds.run +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88741Claude Agent SDK +46
Transparency & trust7%8.88352Claude Agent SDK +31
Negative events≤15-6-2
TotalBB 72.1/100C 56.5/100

Facts side by side

FactClaude Agent SDKguilds.run
KindAgent frameworkAgent framework
VendorAnthropicCigale AI
Hosted endpointno (local only)no (local only)
Transports
AuthAPI keyAPI key
PricingFreeFree
x402nono
LicenceMIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)AGPL-3.0-only
Read-only variant documentednono
llms.txtyesno
Last release2026-09-30none
Terms last updatedno date givenno document linked
Privacy policy last updatedno date givenno document linked
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk57 stars

Verdicts

Claude Agent SDK

Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks. Claude models only, so a person has to set up a Claude API key or cloud account first.

guilds.run

A self-hosted multi-agent system that records each run's prompt, tool calls and memory changes, with per-agent models and tools and no telemetry by default. Public since 9 October 2026, it has no tagged release or published package, its own security register lists 13 open issues, and the site's terms and privacy links return 404.

Before you call either

Claude Agent SDK

  1. Set DISABLE_TELEMETRY=1 before the first run on the Claude API
  2. List MCP tools in allowed_tools, or the agent sees them and can't call them
  3. Pass permission_mode explicitly. An unset mode can start in auto mode since TypeScript 0.3.286
  4. Pin the version. Releases land almost daily and some get yanked
  5. Check the init message for MCP servers in failed or needs-auth. They don't raise

guilds.run

  1. Keep the box on loopback or behind an authenticating proxy with AUTH_MODE=trusted-header. The default mode does not authenticate
  2. Put agents that hold different secrets or GitHub tokens on different machines. Agents on one machine can read each other's homes and tokens
  3. Back up the .env file written by ./setup.sh. It holds the only copy of the key that encrypts stored credentials
  4. Set a spend limit at your model provider. guilds.run sets no spend cap, and max_tool_calls defaults to 50 per run
  5. Pin a commit of main when you deploy. There are no tagged releases or versioned images yet

Questions

Which is better for AI agents, Claude Agent SDK or guilds.run?

Claude Agent SDK scores 72.1 (BB) on agent readiness against guilds.run's 56.5 (C), and leads in 6 of 7 scored categories. guilds.run leads on payments & pricing.

Are Claude Agent SDK and guilds.run open source?

No open-source release is listed for Claude Agent SDK. guilds.run is open source (AGPL-3.0-only).

Other comparisons with Claude Agent SDK or guilds.run

Disclosure

Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report