agent
Open source
free (OSS) + managed cloud tiers
4.3/5

Mem0 (agent memory API)

Drop-in memory layer for LLM agents. Vector + graph memory variants (Mem0g) — the graph variant builds a directed labeled knowledge graph alongside the vector store, with conflict detection on contradictory facts. Leads the 2026 agent-memory benchmarks at 68.4% LLM Score on multi-hop questions. Works with any LLM, including local Ollama models.

By Fredoline Eruo·Last verified May 6, 2026·28,000 GitHub stars

Overview

Drop-in memory layer for LLM agents. Vector + graph memory variants (Mem0g) — the graph variant builds a directed labeled knowledge graph alongside the vector store, with conflict detection on contradictory facts. Leads the 2026 agent-memory benchmarks at 68.4% LLM Score on multi-hop questions. Works with any LLM, including local Ollama models.

Pros

  • Drop-in API — minutes to integrate
  • Graph memory (Mem0g) leads 2026 benchmarks
  • Conflict detection on contradictory facts
  • Works with local LLMs

Cons

  • Cloud tier required for production scale
  • Graph extraction is LLM-cost heavy
  • Less control than Letta's explicit OS-style approach

Compatibility

Operating systems
macOS
Linux
Windows
GPU backends
n/a
LicenseOpen source · free (OSS) + managed cloud tiers

Get Mem0 (agent memory API)

Frequently asked

Is Mem0 (agent memory API) free?

Mem0 (agent memory API) has a paid tier (free (OSS) + managed cloud tiers). Check the pricing page for current terms.

What operating systems does Mem0 (agent memory API) support?

Mem0 (agent memory API) supports macOS, Linux, Windows.

Which GPUs work with Mem0 (agent memory API)?

Mem0 (agent memory API) supports n/a. CPU-only inference is also possible but slow.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.