agent-fabric
Comparisons
vs LangChain

Veridex vs LangChain

LangChain is the most popular Python/JS framework for LLM apps. It excels at prototyping. We have repeatedly hit ceilings when taking LangChain apps to production:

DimensionLangChainVeridex
LoopAgentExecutor reducer; opaque state mutationEvent-sourced; every transition is a typed event (ADR-0049)
ContextConversationBufferMemory (replay) → manual summariseStrict VeV_e, per-section budgets, deterministic compiler (Context Compilation)
MemoryVector store as a toolFour tiers + reconciler with provenance, confidence, lifecycle (Memory)
ToolsTool (function + name + schema)Typed contract + safety class + sandbox + idempotency (Tools)
PolicyAd-hoc try/except, prompt-based guardrailsPriority-ordered, replayable rules; policy packs (Policy)
Approvalshuman_input tool; no durable suspensionFirst-class escalate verdict; checkpoint/resume (Approvals)
AuditCallbacks; structured but not signedHash-chained, signed Evidence Bundles (Observability)
EvalsLangSmith (good, external)Built-in stateful harness + red-team corpus
Multi-tenancyBring-your-ownOpt-in control plane
Type discipline (TS)MixedFirst-class TypeScript

"But I have a working LangChain app"

You don't have to rewrite it.

import { fromLangChainTool, veridexNode } from '@veridex/agents-adapters';
 
// Import existing LangChain tools:
const tools = existingTools.map(t => fromLangChainTool(t));
 
// Or run a Veridex agent inside an existing LangGraph:
const graph = new StateGraph(MyState)
  .addNode('treasury', veridexNode({ agent: treasuryAgent, /* ... */ }));

See Live Bridges for the migration playbook.

When to stay on LangChain

  • Prototypes that don't need policy/audit/checkpoints.
  • Pure data-processing pipelines.
  • Teams already deep in LangChain whose use case doesn't justify migration.

When to choose Veridex

  • High-stakes domains (treasury, healthcare, legal).
  • Long-running agents (>30 turns; hours-to-days workflows).
  • Compliance requirements (auditable trail, signed evidence).
  • Multi-tenant fleets.
  • Adversarial threat models (TPA, prompt injection, replay).