Botpress LLMz vs Lindy AI Memory

Botpress LLMz vs Lindy AI Memory: side-by-side comparison of two framework-embedded memory systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.

Botpress LLMz · Lindy AI Memory

Cost & capability

Botpress LLMzLindy AI Memory
Capability bandcompetentcompetent
Capability composite5555
Cost tierpremiumpremium
Use casesMemory Augmented Chat, Scoped Agentic, Long Running SessionLong Running Session, Memory Augmented Chat, Scoped Agentic

Where they differ (9)

Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.

Botpress LLMzLindy AI Memory
Use casesMemory Augmented Chat, Scoped Agentic, Long Running SessionLong Running Session, Memory Augmented Chat, Scoped Agentic
TypeVector DB + LLMz engine + KBSelective KV memory injected into prompt
Created2017 (Botpress open-sourced on GitHub January 2017, founded by Sylvain Perron and Justin Watson)2023-01 (Lindy AI founded and launched January 2023 by Flo Crivello; YC W23)
PricingFree 500 msgs/mo; Plus $89/mo 1GB Vector DB; Team $495/mo 2GB; Enterprise custom; AI Spend billed separately per LL…Free plan; Plus $49.99/mo; Pro $99.99/mo; Max $199.99/mo; Enterprise custom with SSO/SCIM/audit logs
Funding$40M total; Series A $15M 2021; Series B $25M Jun 2025; Inovia Capital backed$49.9M total; Series B $35M Jan 2023; Battery Ventures key investor; YC W23
DeploymentBoth (OSS self-hosted; Botpress Cloud SaaS; private cloud option)Managed cloud only (SaaS)
MCPvia official adapter — Botpress MCP integrationsearched not found
Optimised forconversational AI + per-plan vector quota + KBselective high-signal memory injection
Anti-fitsearched not foundnot for code-first developers

At a glance

Botpress LLMzLindy AI Memory
SectionFramework-embedded memory Framework-embedded memory
TierT1 T1
TypeVector DB + LLMz engine + KB Selective KV memory injected into prompt
Created2017 (Botpress open-sourced on GitHub January 2017, founded by Sylvain Perron and Justin Watson) 2023-01 (Lindy AI founded and launched January 2023 by Flo Crivello; YC W23)
PricingFree 500 msgs/mo; Plus $89/mo 1GB Vector DB; Team $495/mo 2GB; Enterprise custom; AI Spend billed separately per LL… Free plan; Plus $49.99/mo; Pro $99.99/mo; Max $199.99/mo; Enterprise custom with SSO/SCIM/audit logs
Funding$40M total; Series A $15M 2021; Series B $25M Jun 2025; Inovia Capital backed $49.9M total; Series B $35M Jan 2023; Battery Ventures key investor; YC W23
Backend storagesearched not found searched not found
DeploymentBoth (OSS self-hosted; Botpress Cloud SaaS; private cloud option) Managed cloud only (SaaS)
API surfacesearched not found searched not found
Embeddingsearched not found searched not found
Multi-tenancysearched not found searched not found
MCPvia official adapter — Botpress MCP integration searched not found
A2Asearched not found searched not found
OpenTelemetrysearched not found searched not found
Optimised forconversational AI + per-plan vector quota + KB selective high-signal memory injection
Anti-fitsearched not found not for code-first developers

Taxonomy

AxisBotpress LLMzLindy AI Memory
storagevectorkv
retrievalsimilarityinjection
persistencecross-sessioncross-session
updateextractionextraction
unitdocumentfact
governanceinspectableuser-controllable
conflictllm-arbitratellm-arbitrate

Pros & cons

Botpress LLMz

Pros: Focused on conversational bot deployments at scale — memory is structured around conversation lifecycle (handoff, escalation, return).

Cons: Bot-builder market positioning narrows applicability; less relevant for general agentic apps.

Lindy AI Memory

Pros: Lifelong-agent positioning — memory isn't a feature but the product premise; most opinionated about memory of any framework.

Cons: Closed ecosystem; lock-in risk is highest of the framework-embedded options.

Rows last verified 2026-05-14 / 2026-05-14. Data is CC-BY-4.0 — see how to read this.