Agent memory systems with LangSmith integration
Agent memory systems with first-class LangSmith trace export for agent observability. Ranked by maturity tier.
8 systems match this filter
Tier 1 — battle-tested (7)
- Mem0 Vector + graph + KV (hybrid)
Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.
- Zep & Graphiti Bi-temporal knowledge graph
Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.
- Google Gemini Memory Personal Context + Personal Intelligence
Gemini app learns from past chats via the Personal context setting (on by default, can be disabled; temporary chats excluded). Users can import memories and full chat history from ChatGPT, Claude and other assistants (18+, personal accou…
- Graphiti MCP Server (Zep) Temporal KG with bi-temporal edges
Tracks how facts change over time; maintains provenance; supports prescribed and learned ontology. Bi-temporal edges (when known vs when valid). Only server that distinguishes "fact learned" from "fact true."
- Grok Memory (xAI) Preference-distillation + user-deletable
Extracts and persists facts from past conversations; applies them to future responses. Per-memory deletion UI; user can also clear all. Announced by xAI's official Grok account on 2025-04-17 ('Grok now remembers your conversations').
- Mistral Le Chat — Memories (now Vibe) Graph-contextual + explicit + implicit
Le Chat is now Vibe; Mistral's help center describes Memories as a Vibe feature (article dated 2026-08-12). Memories in Mistral's consumer assistant: saves details on user request or automatically; user can view/edit/delete or clear all;…
- Mistral Vibe (Remote Agents) + Mistral Medium 3.5 Cloud-hosted async coding agents with teleportable session state
Vibe is Mistral's cloud-hosted coding-agent platform: each session runs in an isolated sandbox with task state, history, and approvals. Spawnable from CLI or Le Chat, with parallel execution. Local CLI sessions can be "teleported" to the…
Tier 2 — production-ready (1)
- Vertex AI Memory Bank (now Agent Platform Memory Bank) Managed Vertex memory service
Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterprise Agent Platform. LLM-based memory extraction/consolidation from sessions (background, multimodal, custom topics), per-identity isolation, similarit…