Agent memory systems with MCP support

Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.

Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.

Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.

Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .

Limited native hybrid (users build RRF custom). Fast Rust core (v2.5).

"Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

Agent memory store for both short-term (document) and long-term (vector). LangGraph checkpointer for stateful agents. Vector search extended to Community Edition (Sept 2025).

Knowledge-graph-based persistent memory MCP server — the canonical reference implementation. npx -y @modelcontextprotocol/server-memory ; configurable via MEMORY_FILE_PATH .

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…

The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers t…

Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).

Memory engine with API, app, browser extension, and MCP server. Extracts facts, tracks updates, resolves contradictions, auto-forgets expired info. Plugins for Claude Code, OpenCode, OpenClaw, Hermes.

Voice-AI developer platform — STT + LLM + TTS pipelines wired to telephony (Twilio / SIP). Used to build outbound + inbound phone agents at scale. Raised $20M Series A from Bessemer + Y Combinator (Dec 2024) at $130M valuation; revenue r…

Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.

Runtime enforcement targeting memory poisoning, unauthorised execution, identity spoofing per the OWASP LLM threat list. Visibility/control over MCP servers and locally-installed AI tools — the infrastructure layer where memory is most e…

NeuralSearch combines vector + keyword via neural hashing — compresses to 1/10th size while retaining 99% info. AI-powered personalisation + recommendations.

Background sub-agent in Claude Code that periodically scans ~/.claude/projects/<project>/memory/ + recent JSONL transcripts via grep, prunes stale notes, deduplicates, resolves contradictions, converts relative dates to absolute timestam…

Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.

Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. M…

Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.

Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-…

Cloud browser infrastructure for AI agents. Headless Chromium sessions with persistent cookies, localStorage, session recording — agent workflows carry state across runs. Memory at the session/automation tier rather than conversational.

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.

Anthropic's Chrome extension that lets Claude act inside the user's existing browser (rather than a sandboxed one). Research preview launched August 2025 — limited to Claude Max tier. Distinct from Anthropic Computer Use (which is the AP…

Hooks into Claude Code's session lifecycle; compresses tool outputs into ~500-token observations via Claude's agent SDK. SQLite + FTS5 with optional Chroma vector. "Endless Mode" compresses in-flight to extend session length. Captures wh…

High-performance MCP server building persistent code knowledge graphs via AST. 155 languages via vendored tree-sitter; SQLite + WAL; single static binary; zero runtime deps. Knowledge graph: Project/Package/File/Module/Class/Function/Met…

Enterprise contact centre (voice + chat). Short-term covers current session; long-term persists across sessions and is shared by every agent a customer might encounter. Most explicitly engineered memory model in the segment.

Cross-listing of Cognition's Devin product framed at the harness level rather than the memory layer. Devin 2.0 (Mar 2025) added cheaper concurrent sessions; Spec Mode (Aug 2025, post-Windsurf-IP acquisition) integrates Windsurf-style spe…

AI-first IDE that forked VS Code; Composer (multi-file edit) and Agent Mode (long-running coding agent) are its flagship surfaces. Memory layer = .cursorrules / Rules; recall via repo-aware Context Engine. Anysphere (parent) raised $900M…

Storage-optimised index scaling to billions of vectors. Hosted MCP servers for UC functions, Genie, Vector Search. Agent framework integrates retrieval with Unity Catalog governance.

Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads …

The Browser Company's AI-native browser; acquired by Atlassian for $610M (Sept 2025). Stores summaries and preferences locally; opt-in @history feature references up to 7 days of browsing as context. History/chats/bookmarks encrypted loc…

e2b provides secure, ephemeral sandboxes (Firecracker microVMs) for AI agent code execution. Each sandbox spins up in <200ms with full Linux environment, Python/Node/etc preinstalled. Substrate for code-agent products including Anthropic…

Mature hybrid (BM25 + vector) implementations. RRF + weighted combination. Elastic ELSER sparse model.

Applies guardrails at three points: (1) before write to vector DB, (2) before query reaches embedding model, (3) before response. Detects malicious instructions in stored memory before retrieval; scans for PII/PHI in/out. Text + image + …

Visual LangChain canvas. LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by internal chat_message DB table. Buffer Window limits to last K interactions; Summary Buffer compresses older turns whil…

Treats memory as first-class in multi-agent tracing. Luna-2 SLMs (3B / 8B) scan every interaction for intent drift and belief drift; 20+ checks at sub-200ms latency. Catches when agent A's view of the world splits from teammate B's. Open…

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 …

GitHub's hosted agentic workspace — given an issue, generates a spec, plan, and PR. Preview launched April 2024; rebranded "GitHub Copilot Coding Agent" + "Copilot Agent Mode" in 2025 with broader GA. Backed by Microsoft Azure OpenAI + A…

Enterprise search with 100+ connectors. Personalised per-user knowledge graph. No governance layer.

Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).

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."

Targets the supply-chain / lineage layer rather than runtime memory writes. Model Genealogy tracks training/fine-tuning/modification history — catches poisoning baked in during training. AIBOM generates auditable inventory of model compo…

Spec-driven agentic IDE from AWS — preview launch July 2025. Codifies the AI-coding workflow as Requirements / Design / Tasks files generated before code ("specs"); also persists "steering" files and Hooks. Built as a VS Code fork; runs …

Agent component has built-in chat memory enabled by default, keyed by session ID. Custom session IDs isolate per-user history. Bundled Mem0 + Redis integrations for external memory layers.

Memory module reads/writes captured as named spans. Trace Log View concatenates every agent step including memory ops. Agent Graphs (GA 2025) infer graph structure from observation nesting; session-level replay tracks how memory state ev…

Memory reads, vector DB retrievals, state changes are distinct span types in traces. RAG eval separates retrieval quality (context precision) from generation quality (faithfulness). Dataset versioning guards against eval drift.

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 .

Continuously captures screen + audio + wearable input; AI search across the timeline. Privacy-first (local-first storage). Originated as Rewind macOS app; pivoted to wearable + lifelog product.

LiveKit Agents — agent framework built on LiveKit's open-source WebRTC media server. LiveKit raised $45M Series B Sep-2024 ($300M val). Powers OpenAI Realtime API's WebRTC transport (LiveKit is the substrate OpenAI chose). Agents framewo…

Mem0's managed cloud API exposed as MCP tools. Semantic search + CRUD on memories scoped by user / agent / session. Cloud-hosted MCP endpoint — no local infrastructure required.

Commercial Mem0 ships SOC 2 / HIPAA, zero-trust access controls, BYOK encryption, real-time monitoring, audit logs, workspace governance as defaults. OpenMemory is the local self-hosted variant (Docker + FastAPI + Postgres + Qdrant) for …

Microsoft 365 Copilot memory stored in user's Exchange mailbox with compliance alignment. GA Jul 2025.

Mistral's Agents API provides persistent conversation state across turns and sessions; runtime maintains branching conversation trees. Memory is implicit in the stateful session model rather than a separate store — agents can branch, con…

Le Chat Memories — graph-based, context-aware. Stores user preferences and past decisions; memories saved explicitly (user instruction) or inferred automatically. Coupled to "Work Mode" agentic layer.

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…

Low-code workflow platform. AI Agent node ships with pluggable memory sub-graph: Simple Memory for development; Postgres/Redis for production; vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall.

Notion's first-party AI. Reads up to 50 pages per query (as of Jan 2026); Custom Instructions persist brand voice / team structure / preferences. Context follows you across model swaps. Notably not persistent cross-session learning — it …

First-party memory in ChatGPT; auto-extracts persistent facts about the user across sessions. Apr 2025 expansion to chat-history referencing.

Memory under ~/.codex/memories/ : summaries, durable entries, recent-input logs, supporting evidence — generated in background after sessions go idle. Chronicle (opt-in macOS preview) uses screen-capture to seed memory. Off by default; o…

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.…

AI-native Chromium-based browser. Assistant operates across tabs and sessions; persistent memory of preferences; multi-step agentic tasks without leaving the browser. Memory is opt-in and server-side; enterprise memory tier separately av…

Open-source Python framework for real-time voice + multimodal AI agents, maintained by Daily.co. Pipeline-style architecture (STT → context → LLM → TTS) wired over WebRTC. The OSS substrate that many of the voice platforms build on or co…

No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory rel…

Hybrid vector + keyword + semantic reranking. Cortex Agents (GA Nov 2025) orchestrate over Cortex Search for unstructured data. No separate vector infra needed inside Snowflake.

Open-source TypeScript framework for browser automation, maintained by Browserbase. Hybrid of Playwright-style imperative APIs and AI-driven natural-language actions (e.g. page.act('click the sign-up button')). Used as the OSS substrate …

Codeium-built agentic IDE (VS Code fork); flagship was Cascade — a planning + execution agent that maintains "Flows" and "Memories" as durable artifacts. Reported acquired by OpenAI in May 2025 for ~$3B (later partly unwound — Google pai…

Native (Rust) collaborative code editor by Zed Industries (founded by the Atom + Tree-sitter team). Added Agentic Editing in 2024 — multi-step coding agent driven by Claude or local models; .rules markdown + Threads form the memory layer…

Bi-temporal knowledge graph preserves full lineage of every stored fact — every memory write traceable and auditable by graph schema, not bolted-on logging. SOC 2 Type II; HIPAA BAA available; BYOK + VPC-isolated deployment for data resi…

Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Red…

AWS managed memory service for agents running on Bedrock AgentCore. Native integrations with LangChain/LangGraph and Strands. Drives long-running MCP servers + agent workloads.

Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).

ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.

Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.

When Mem0 is connected, gains Memory Operation Timeline, Search Analytics, Memory Growth tracking, Error Tracking per memory call. Standalone, records context at each step but doesn't analyse memory quality.

Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.

Agent-memory product. LLM-curated hierarchical context.