Botpress LLMz vs n8n AI Agent Memory
Botpress LLMz vs n8n AI Agent Memory: side-by-side comparison of two framework-embedded memory systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.
Cost & capability
| Botpress LLMz | n8n AI Agent Memory | |
|---|---|---|
| Capability band | competent | competent |
| Capability composite | 55 | 60 |
| Cost tier | premium | premium |
| Use cases | Memory Augmented Chat, Scoped Agentic, Long Running Session | Scoped Agentic, Memory Augmented Chat, Long Running Session |
Where they differ (13)
Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.
| Botpress LLMz | n8n AI Agent Memory | |
|---|---|---|
| Capability composite | 55 | 60 |
| Use cases | Memory Augmented Chat, Scoped Agentic, Long Running Session | Scoped Agentic, Memory Augmented Chat, Long Running Session |
| Type | Vector DB + LLMz engine + KB | Pluggable buffer + Postgres/Redis + vector |
| Created | 2017 (Botpress open-sourced on GitHub January 2017, founded by Sylvain Perron and Justin Watson) | 2019-10 (n8n platform launched Oct 2019; AI Agent node added in n8n 1.x era 2023-2024) |
| License | MIT (SDK/integration packages in botpress/botpress) | Sustainable Use License + n8n Enterprise License (fair-code, source-available; not OSI) |
| GitHub | botpress/botpress — ~14.9k stars | n8n-io/n8n — ~208k stars, last release 2026-10 |
| Pricing | Free 500 msgs/mo; Plus $89/mo 1GB Vector DB; Team $495/mo 2GB; Enterprise custom | Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo (40k executions) |
| Funding | $40M total; Series A $15M 2021; Series B $25M Jun 2025; Inovia Capital backed | $253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); prior Series B €55M Mar 2025 |
| Deployment | Both (OSS self-hosted; Botpress Cloud SaaS; private cloud option) | Self-hosted (Docker / npm); cloud via n8n.cloud SaaS |
| MCP | via official adapter — Botpress MCP integration | via official adapter — n8n MCP node |
| OpenTelemetry | searched not found | via adapter — Langfuse / OTel community |
| Optimised for | conversational AI + per-plan vector quota + KB | low-code workflow + pluggable memory |
| Anti-fit | searched not found | not for code-first agent stacks (low-code workflow positioning) |
At a glance
| Botpress LLMz | n8n AI Agent Memory | |
|---|---|---|
| Section | Framework-embedded memory | Framework-embedded memory |
| Tier | T1 | T1 |
| Type | Vector DB + LLMz engine + KB | Pluggable buffer + Postgres/Redis + vector |
| Created | 2017 (Botpress open-sourced on GitHub January 2017, founded by Sylvain Perron and Justin Watson) | 2019-10 (n8n platform launched Oct 2019; AI Agent node added in n8n 1.x era 2023-2024) |
| Latest release | — | n8n@2.44.4 (2026-10-19) |
| License | MIT (SDK/integration packages in botpress/botpress) | Sustainable Use License + n8n Enterprise License (fair-code, source-available; not OSI) |
| GitHub | botpress/botpress — ~14.9k stars | n8n-io/n8n — ~208k stars, last release 2026-10 |
| Pricing | Free 500 msgs/mo; Plus $89/mo 1GB Vector DB; Team $495/mo 2GB; Enterprise custom | Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo (40k executions) |
| Funding | $40M total; Series A $15M 2021; Series B $25M Jun 2025; Inovia Capital backed | $253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); prior Series B €55M Mar 2025 |
| Backend storage | searched not found | searched not found |
| Deployment | Both (OSS self-hosted; Botpress Cloud SaaS; private cloud option) | Self-hosted (Docker / npm); cloud via n8n.cloud 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 | via official adapter — n8n MCP node |
| A2A | searched not found | searched not found |
| OpenTelemetry | searched not found | via adapter — Langfuse / OTel community |
| Optimised for | conversational AI + per-plan vector quota + KB | low-code workflow + pluggable memory |
| Anti-fit | searched not found | not for code-first agent stacks (low-code workflow positioning) |
Taxonomy
| Axis | Botpress LLMz | n8n AI Agent Memory |
|---|---|---|
| storage | vector | vector |
| retrieval | similarity | similarity |
| persistence | cross-session | cross-session |
| update | extraction | append-only |
| unit | document | episode |
| governance | inspectable | inspectable |
| conflict | llm-arbitrate | append-only |
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.
n8n AI Agent Memory
Pros: n8n's workflow-orchestration backbone gives agents memory tied to durable workflow state — not just chat history.
Cons: Memory features are still maturing relative to dedicated memory layers; thin documentation on eviction policy.