Agent memory systems with OpenTelemetry support
Agent memory systems that emit OpenTelemetry traces and spans — open-standard observability that plugs into Tempo, Jaeger, Honeycomb, or any OTel backend. Ranked by maturity tier.
26 systems match this filter
Tier 1 — battle-tested (26)
- Anthropic Claude (foundation models) Frontier foundation model family (Sonnet 4 / Opus 4.5 / Haiku 4.5)
Claude family of frontier foundation models — Sonnet 4 (workhorse), Opus 4.5 (frontier capability), Haiku 4.5 (fast/cheap). Frontier model used as substrate by Claude Code, Anthropic Memory tool, Cline, Aider, Continue.dev, Cursor, Goose…
- Neo4j Property graph + vectors + Aura Agent
Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.
- Amazon Neptune Analytics Vector + graph in one managed service
Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025; Cognee integration for agentic RAG. Combines semantic recall with multi-hop traversal in one managed service.
- LangGraph (orchestration) Stateful agent graph runtime
LangChain's stateful graph runtime for agents — explicit state, persistence, time-travel debugging, human-in-the-loop. Memory is one persistence target (LangGraph Persistence cross-listed).
- LanceDB Embedded Arrow-columnar vector DB
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
- Claude Code (Anthropic) Terminal-native agentic coding harness
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as th…
- Amazon Q Developer AWS-hosted developer AI agent + IDE plugins
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troublesh…
- Anthropic Computer Use Beta agent capability for Claude
Claude 3.5 Sonnet's beta capability for controlling a computer (mouse, keyboard, screen). Frame for browser-agent and OS-agent products built on Claude.
- Anthropic Computer Use Claude desktop-control capability (Anthropic API)
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Clau…
- Arize Phoenix OSS LLM tracing + eval
Arize AI's open-source LLM observability tool — OpenTelemetry-native LLM tracing, evals, datasets. Arize commercial offers Phoenix + Surveyor.
- AutoGen / AG2 Multi-agent conversation framework
Originally Microsoft Research's multi-agent framework — fork branded AG2 (2024-10) led by community. Memory is one optional component (AutoGen Memory cross-listed).
- Braintrust Eval + observability for AI
Eval-first LLM platform — datasets, eval runs, prompt playground, tracing. Founded by ex-Impira (acquired by Dropbox) team. Used by Notion, Brex, AirOps.
- Claude Code auto-memory Per-project file directory
Persistent file-based memory at ~/.claude/projects/<project>/memory/ with a MEMORY.md index plus typed memory files (user / feedback / project / reference). Loaded into context across sessions.
- CLAUDE.md Git-backed persistent instructions
Markdown file injected at session start; reloaded post-compaction. Document-as-memory: human-readable, version-controlled, no extraction or vector store. Anthropic-canonical pattern; equivalent emerges in Cursor / Windsurf.
- Continue.dev (framework) Open coding assistant
Open-source AI coding assistant — VS Code / JetBrains; configure-your-own-models. Existing Continue-rules row covers file-backed memory; this row covers the framework.
- CrewAI Multi-agent orchestration
Multi-agent framework — Crews (sequential) + Flows (event-driven). Open-source core + CrewAI Enterprise. Memory available via Mem0 / Letta adapters (CrewAI Memory cross-listed).
- Datadog Bits AI Observability AI agent / SRE copilot
Datadog's AI-assistant for observability — incident summarisation, root-cause hypotheses, runbook automation. Bits AI launched Aug-2023, GA 2024 across the Datadog suite. Datadog parent: $2.7B+ revenue 2024; NASDAQ:DDOG.
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) Long-running agent memory with continuous event-streaming consolidation
GA at Google Cloud Next 2026 (2026-04-22). Vertex AI rebranded as Gemini Enterprise Agent Platform; Memory Bank now "Agent Platform Memory Bank" with new continuous event-streaming + automated memory generation triggered by configurable …
- Google Gemini Memory Personal Context + Personal Intelligence
Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).
- Letta / MemGPT Tiered: core / recall / archival
LLM-as-Operating-System paradigm — model manages its own memory, paging between core context, recall buffer, and archival store. UC Berkeley origin; transitioning to letta_v1_agent .
- Microsoft Copilot Memory Org / tenant-scoped (Exchange-backed)
Microsoft 365 Copilot memory stored in user's Exchange mailbox with compliance alignment. GA Jul 2025.
- OpenAI Agents SDK OpenAI's official agent framework
OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.
- OpenAI Codex CLI Terminal-native agentic coding harness (OpenAI)
OpenAI's open-source terminal coding agent — released April 2025 alongside o3/o4-mini. Counterpart to Claude Code in the OpenAI stack. Memory via ~/.codex/memories (file-backed); routes to OpenAI o-series and Codex (model) for execution.…
- OpenAI Realtime API Speech-to-speech LLM API (OpenAI Realtime)
OpenAI's Realtime API for native speech-to-speech multimodal interaction with GPT-4o — launched Oct 2024 (DevDay). Skips the STT → LLM → TTS pipeline by passing speech directly to GPT-4o. The platform substrate that Vapi/Retell/Bland int…
- Sourcegraph Cody (agent) Code-intelligence-backed coding assistant + Agentic Chat
Sourcegraph's coding assistant — IDE plugin (VS Code, JetBrains) plus web. Distinguishes itself with Sourcegraph's code-search index as the context provider (cross-repo, codebase-wide retrieval). Agentic chat added 2024; runs Claude / GP…
- v0 (Vercel) Vercel's AI app builder — prompt-to-Next.js component/app
Vercel's AI product (formerly v0.dev) that generates React/Next.js components and full apps from natural-language prompts. Tight integration with Vercel deploy; uses Vercel-hosted models (multi-LLM). Differentiator: best-in-class shadcn/…