MeshFlow
  • Cloud PlatformDeployIntegrationsInit CLIWhy MeshFlow
  • DocsLearn
  • CustomersCertificationBlogChangelogCommunity
  • Pricing
Sign inGet started
Pricing
Sign inGet started
MeshFlow

The production-safe standard for agentic AI.
Apache 2.0 — free forever.

Product
  • Pricing
  • Cloud
  • Compare
  • Init CLI
  • Changelog
Docs
  • Quickstart
  • Core concepts
  • Compliance guide
  • Token optimization
  • API reference
Resources
  • Blog
  • Customers
  • Community
  • PyPI
  • GitHub
Company
  • Discord
  • Twitter
  • Security
  • License
MeshFlow © 2026 · Yaya Systems · Apache 2.0
All systems operational
MeshFlowdocs
Search docs...⌘K
v1.13.0 GitHub Discord
Getting startedQuickstartInstallationCore conceptsHarness architectureSkills vs ToolsSandbox mode
GuidesBuilding agentsMulti-agent workflowsModel RoutersCost AnalyticsCompliance guideToken optimization
Claude & AIAdvisor patternThinking budgetsDynamic workflowsContext compactionTool streaming
Governancemeshflow-forensicZero-Trust PoliciesSOC 2 assertionEU AI ActProduction Readiness
IntegrationsOpenAI Agents SDKLangGraphCrewAIMCP ToolsTypeScript SDKOTel / OTLPAutoGen 0.4+
API ReferenceWorkflowAgentCostCapAdvisorAgentCostRegressionGate
Docs/Core concepts

Core concepts

MeshFlow's public API centers on Agent, Team, Workflow, StateGraph, ComplianceProfile, StepRuntime, and EvalSuite. The high-level Workflow wrapper is the fastest path; Team and StateGraph give you deeper control.

The production pit of success

MeshFlow is designed as a "pit of success" — the default path is the safe path. You have to opt out of safety features, not opt in. Every workflow is durable, audited, compliance-checked, and cost-capped unless you explicitly disable it.

Design principle
Safety features are removable but never absent by default. The hardest thing MeshFlow could do is make production safety invisible — and that's exactly what it does.
Previous
Installation
Next
Building agents
On this pageThe production pit of success