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 LLMz | Lindy AI Memory | |
|---|---|---|
| Capability band | competent | competent |
| Capability composite | 55 | 55 |
| Cost tier | premium | premium |
| Use cases | Memory Augmented Chat, Scoped Agentic, Long Running Session | Long 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 LLMz | Lindy AI Memory | |
|---|---|---|
| Use cases | Memory Augmented Chat, Scoped Agentic, Long Running Session | Long Running Session, Memory Augmented Chat, Scoped Agentic |
| Type | Vector DB + LLMz engine + KB | Selective KV memory injected into prompt |
| Created | 2017 (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) |
| Pricing | Free 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 |
| Deployment | Both (OSS self-hosted; Botpress Cloud SaaS; private cloud option) | Managed cloud only (SaaS) |
| MCP | via official adapter — Botpress MCP integration | searched not found |
| Optimised for | conversational AI + per-plan vector quota + KB | selective high-signal memory injection |
| Anti-fit | searched not found | not for code-first developers |
At a glance
| Botpress LLMz | Lindy AI Memory | |
|---|---|---|
| Section | Framework-embedded memory | Framework-embedded memory |
| Tier | T1 | T1 |
| Type | Vector DB + LLMz engine + KB | Selective KV memory injected into prompt |
| Created | 2017 (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) |
| Pricing | Free 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 storage | searched not found | searched not found |
| Deployment | Both (OSS self-hosted; Botpress Cloud SaaS; private cloud option) | Managed cloud only (SaaS) |
| API surface | searched not found | searched not found |
| Embedding | searched not found | searched not found |
| Multi-tenancy | searched not found | searched not found |
| MCP | via official adapter — Botpress MCP integration | searched not found |
| A2A | searched not found | searched not found |
| OpenTelemetry | searched not found | searched not found |
| Optimised for | conversational AI + per-plan vector quota + KB | selective high-signal memory injection |
| Anti-fit | searched not found | not for code-first developers |
Taxonomy
| Axis | Botpress LLMz | Lindy AI Memory |
|---|---|---|
| storage | vector | kv |
| retrieval | similarity | injection |
| persistence | cross-session | cross-session |
| update | extraction | extraction |
| unit | document | fact |
| governance | inspectable | user-controllable |
| conflict | llm-arbitrate | llm-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.