← Leaderboard
7.3 L3

Twenty Crm

Ready Assessed · Docs reviewed · Mar 21, 2026 Confidence 0.54 Last evaluated Mar 21, 2026

Verify before you commit

Trust read first, source links second, build decision third.

Use this page to sanity-check Twenty Crm quickly. We surface the evidence tier, freshness, and failure posture here, then put the official links where you can actually act on them, especially on mobile.

Evidence

Assessed

Docs reviewed · Mar 21, 2026

Freshness

Updated 2026-03-21T22:38:21.472663+00:00

Mar 21, 2026

Failures

Clear

No active failures listed

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

7.5
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

7.0
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

7.3

Autonomy breakdown

P1 Payment Autonomy
G1 Governance Readiness
W1 Web Agent Accessibility
Overall Autonomy
Pending

Active failure modes

No active failure modes reported.

Reviews

Published review summaries with trust provenance attached to each card.

How are reviews sourced?

Docs-backed Built from public docs and product materials.

Test-backed Backed by guided testing or evaluator-run checks.

Runtime-verified Verified from authenticated runtime evidence.

Twenty CRM: API Design & Integration Surface

Docs-backed

Twenty's primary API is GraphQL with a well-documented schema introspectable at /metadata. REST API is available for some endpoints. GraphQL mutations cover create, update, delete, and batch operations on CRM objects. Custom objects are first-class in the API. Filtering, pagination (cursor-based), and sorting are supported. API versioning uses major version prefixes. SDK support is limited; direct GraphQL calls are the standard pattern. The API is clean but requires familiarity with GraphQL conventions.

Rhumb editorial team Mar 21, 2026

Twenty CRM: Comprehensive Agent-Usability Assessment

Docs-backed

Twenty is an open-source CRM designed as a modern HubSpot alternative, with a GraphQL API as its primary data interface. Agents can programmatically manage contacts, companies, deals, tasks, and custom objects via the API. The data model is workspace-based with custom field support. Twenty Cloud is a managed offering; self-hosting is supported via Docker. Webhooks are available for CRM events. API key auth is supported. Agent relevance is solid for B2B workflow agents: contact enrichment, deal stage management, and task creation are all API-accessible. Confidence is docs-derived; the product is actively developed and API surface is stabilizing.

Rhumb editorial team Mar 21, 2026

Twenty CRM: Auth & Access Control

Docs-backed

Authentication uses API tokens generated in the Twenty workspace settings. Bearer token auth on all API requests. No OAuth flow for machine-to-machine — API key is the agent auth pattern. Workspace-scoped tokens; no per-resource scoping documented. Token rotation is manual via the dashboard. Straightforward API key model for agent use.

Rhumb editorial team Mar 21, 2026

Twenty CRM: Documentation & Developer Experience

Docs-backed

Documentation at docs.twenty.com covers setup, data model, API reference, and webhooks. GraphQL schema is introspectable. Self-hosting guide is detailed. Community Discord is active. REST API docs are less complete than GraphQL docs. The project is pre-1.0 (as of early 2026); some docs may lag behind the codebase. GitHub is the authoritative source for edge cases.

Rhumb editorial team Mar 21, 2026

Twenty CRM: Error Handling & Operational Reliability

Docs-backed

GraphQL errors return in the standard errors array with message and extensions fields. HTTP 400 for malformed queries, 401 for invalid tokens, 200 with errors array for application-level errors (standard GraphQL pattern). Validation errors include field-level details. No retry-after headers documented. The service is actively developed — breaking changes are possible between minor versions during the pre-1.0 phase.

Rhumb editorial team Mar 21, 2026

Use in your agent

mcp
get_score ("twenty-crm")
● Twenty Crm 7.3 L3 Ready
exec: 7.5 · access: 7.0

Trust shortcuts

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L3 Ready

7.3 / 10.0

Alternatives

No alternatives captured yet.