Skip to content

MemoryLetta

Letta

Stateful agents with structured memory. Successor to MemGPT.

Category
Memory
Pricing
FREEMIUM
Source
Open core
Hosting
Hybrid
Platforms
APICLImacOSWindowsLinux
Models
BYO key / model
Verified
Jul 12, 2026

Open-source framework for building stateful agents — memory blocks, context-window management, tool-use primitives baked in. Useful as a reference architecture for long-running agents.

Capabilities 5

What it actually does — grouped by capability family.

  • Agent framework (primary capability)
  • Tool / function calling (secondary capability)
  • Multi-agent orchestration (secondary capability)
  • Agent memory (primary capability)
  • App / agent deployment (secondary capability)

Pros & cons

  • Self-editing agent memory
  • Open source, model-agnostic
  • REST APIs + multi-language SDKs
  • Reference architecture for memory
  • Developer-focused, not no-code
  • Memory model has a learning curve
  • Younger, evolving framework

Tags

Alternatives to Letta (4)

View all Memory →
  • View mem0 details
    MemoryFREEMIUMOpen core

    mem0

    Mem0

    Long-term memory layer for AI agents. Self-hostable.

    Persistent memory store + retrieval pipeline for agent applications. Handles per-user/per-session/per-agent scope cleanly; pairs with OpenAI, Anthropic, and local models.

    Quick to adopt, broad framework integrations
    Weaker on temporal/state-change queries
    • memory
    • agents
    • rag
    • self-hosted
    Open
  • View Zep details
    MemoryFREEMIUM

    Zep

    Zep

    Temporal knowledge-graph memory for AI agents.

    Memory layer that gives agents long-term context by building a temporal knowledge graph from chat history and business data, tracking how facts evolve over time. It's powered by Graphiti, Zep's Apache-2.0 open-source temporal graph engine, with Zep Cloud offering a managed, credit-based service on top. Used to keep agent context relevant as conversations and data grow.

    Open-source Graphiti engine (Apache-2.0)
    Graph approach has learning curve
    • memory
    • agents
    • knowledge-graph
    • temporal
    • +1
    Open
  • View Cognee details
    MemoryFREEMIUMOpen core

    Cognee

    Cognee

    Open-source memory for AI agents.

    An open-source semantic memory layer for AI agents. Cognee ingests documents, relational data, and system context, then runs an Extract-Cognify-Load pipeline that uses an LLM to build a knowledge graph with embeddings and relationships. Agents query it for durable, cross-session context that captures how concepts connect. Self-host the Python SDK for free, or use the managed cloud tiers.

    Self-hostable Python SDK
    Newer, smaller ecosystem
    • agent-memory
    • knowledge-graph
    • rag
    • open-source
    Open
  • View LangGraph details
    OrchestrationFREEOSS

    LangGraph

    LangChain

    Graph-based agent orchestration. Stateful loops with checkpoints.

    LangChain's agent layer. Model agents as nodes in a state graph with persistent checkpoints, human-in-the-loop steps, and durable execution. Strong when you need a long-running, debuggable agent rather than a one-shot chain.

    Durable checkpointed state
    Steeper learning curve
    • agents
    • graph
    • state
    • open-source
    Open
Open Letta