Self-hostable agent memory systems

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

Acquired by ClickHouse (2026-01-16); product and MIT-licensed repo continue under the Langfuse name. Memory module reads/writes captured as named spans. Trace Log View concatenates every agent step including memory ops. Agent Graphs (GA …

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

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

Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer …

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

Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompt…

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 …

Formerly an NPC character engine with named Long-Term Memory; now sells realtime voice models (TTS-2, STT-1, speech-to-speech) and OpenAI-compatible open-model inference. Character/NPC memory is no longer the headline product.

Acquired by Check Point Software (completed by 2025-11-11); being folded into Check Point's AI security platform. Screens every prompt, response, and retrieved document for indirect prompt injection — primary vector for memory poisoning.…

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.

Acquired by Proofpoint (closed 2026-02-12). 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…

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…

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 + …

AI security platform with four modules: AI asset discovery, supply-chain/model integrity validation, continuous attack simulation, and runtime detection/response, including protection of agents and MCP-based systems.

German enterprise stack. PhariaCatch captures + preserves organisational knowledge through structured human-machine collaboration; PhariaAssistant queries via semantic search. Combines sovereign deployment constraints with explainability…

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.

Acquired by NiCE (closed 2025-09-08); continues as NiCE Cognigy, standalone and inside CXone Mpower. Enterprise contact centre (voice + chat). Short-term covers current session; long-term persists across sessions and is shared by every a…

Mimir hierarchical memory: short-term (verbatim), medium-term (summaries + emotion), long-term (cross-session). Scene awareness layer adds in-engine perception. Unity + Unreal SDKs with real-time voice + lipsync.

Acquired by Cisco (announced 2026-04-09, closed by 2026-05); now Splunk Agent Observability. 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 …

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."

Memory carries forward user-chosen context (matter details, precedent, preferences, approved practices) and reuses past threads scoped to a user, client, matter or firm process. Firm admins enable/disable it; ethical walls and audit cont…

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.

Commercial Mem0 ships SOC 2 / HIPAA, zero-trust access controls, BYOK encryption, real-time monitoring, audit logs and workspace governance as defaults (Trust Center at trust.mem0.ai). For privacy-first deployments the self-hosted path i…

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 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;…

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.

Wearable orb (necklace or clip) with open-source hardware + firmware. Continuous audio capture; real-time GPT-4o transcription; searchable memory graph. Supports app screen capture too. Hybrid privacy: cloud by default (SOC 2/HIPAA/AES-2…

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…

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…

AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, b…

Structured, persistent memory layer for AI agents. Open source.

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).

Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries stati…

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

User-profile-based long-term memory. Per-user profile + event timeline. API + Python/Node/Go SDKs + MCP server. Profile-centric rather than fact-centric.

Microsoft Semantic Kernel's memory plugin (Microsoft.SemanticKernel.Plugins.Memory): a plug-in approach to long-term memory in the SK agent framework (agent memory marked experimental). Semantic Kernel's README names Microsoft Agent Fram…

Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction sta…

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.

SEA-LION-Embedding (March 2026): retrieval + reranking models contrastively trained on 245M text pairs across 10 SE Asian languages. SEA-BED benchmark (169 datasets). SEA-LION v4 (Gemma-based) at 128K context with native function calling.

Renamed Anda Brain (repo now ldclabs/anda-brain). Native graph-based memory for autonomous AI agents. Bio-inspired sleep-based memory consolidation. The hosted service brain.anda.ai has been discontinued; Anda Brain is now self-hosted on…

Tsinghua spinout. Foundation agent series for autonomous smartphone/PC GUI control. Persistent task memory retains shopping history, app usage patterns, multi-step task state across sessions. AutoGLM-Thinking claimed first agent capable …

Stateful AI API combining persistent memory, RAG, web search and routing across many LLMs behind one interface, with SDKs for Python and npm; benchmarks its memory on LoCoMo and LongMemEval. As of Oct 2026 Backboard positions itself as a…

Wraps Supermemory cloud API. Team memory shared across project members, separate from personal memories. Auto-capture on session end; per-repo config.

"Cognify" extracts entities and relationships into a structured graph. Saves interaction patterns as coding rules; uses both vector and graph DBs. Bundled in Cognee v0.3.5+.

Discontinued: Continue was bought by Cursor (announced ~2026-06-16); the product is discontinued and the continuedev/continue repo is read-only. Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP rathe…

Google's Agent Development Kit. Session services: InMemory / Database / VertexAI. Long-term: InMemoryMemoryService or VertexAIMemoryBankService (uses Vertex AI Memory Bank Preview for persistent cross-session memory).

World (facts), Experiences (agent actions), Opinion (beliefs with confidence scores), Observation (mental models). Entity resolution ("Alice" and "my coworker Alice" same node). Mimics human recall topology.

YC F25 'company brain': connects 50+ sources (Slack, Gmail, Notion, Drive...) into a permission-aware context graph served to agents via API/SDK, returning structured results or LLM-ready summaries; learns from queries over time.

First-class memory module inside LangChain — explicit cognitive-science-style typing of memories.

Two-tier model: ChatMessage FIFO queue with overflow flushed into long-term Memory Block objects. Memory class replacing older ChatMemoryBuffer.

Open-source local-first outliner. Notes stored as Markdown / Org-mode on disk. AI integration via community plugins (e.g. logseq-ai for chatting with the graph). Graph view + backlinks; daily-journal-driven workflow.

ByteDance Seed + Zhejiang Univ + SJTU. Multimodal agent with long-term memory as entity-centric graph built from live video + audio streams. Parallel memorisation + control processes. Ships M3-Bench evaluation dataset.

TypeScript-first agent framework. Default memory: LibSQL store + on-device fastembed-js for semantic recall.

SQLite-Vec default, Cloudflare hybrid for production. Typed edges (causes, fixes, contradicts). Autonomous consolidation compresses old memories. SSE real-time notifications + D3.js visualisation dashboard. Agent-pipeline focused (LangGr…

Open-source long-term memory framework for autonomous agents.

Multi-layered open-source memory system for AI agents.

Memory layer from MatrixOrigin. Strong-retrieval / clear-reader-separation design.

Developer-first reference platform for AI wearables. LVMM 2.0 captures visual data through video, encodes it into frames on-device, and stores moments as searchable memories; companion app surfaces past conversations/decisions/experience…

Renamed MemStore (memory.store now redirects to mem.store); YC Spring 2026. Shared memory layer delivered as an MCP server: a team's AI agents record decisions/progress across sessions and recall from teammates' stores with sources attac…

Renamed NVIDIA CMX Context Memory Storage Platform (2026). A BlueField-4 (STX) powered "AI-native context tier" that extends GPU memory with a shared pod-level KV-cache tier for long-context, multi-turn agentic inference, with Dynamo rou…

Now positioned as 'The data factory for AI': connects AI labs with licensed data and an expert network, built on an identity graph of ~2.2B people and 380M businesses; people-data APIs (identity resolution, enrichment, search) for applic…

Omni memory system for personalised, long-horizon, self-evolving agents. From OPPO PersonalAI.

Obsidian community plugin. Generates embeddings locally with a bundled model (TaylorAI/bge-micro-v2, 384-dim); chat with notes + see semantically related links. No API key required for local; supports 100+ cloud models optionally. Privac…

OpenAI's agent SDK. Sessions for working context within an agent loop; RunContextWrapper for structured persistent state. April 2026 update added categorised long-term memory: project / user / policy. Long-term tier typically backed by e…

Renamed LongMemory (repo CaviraOSS/LongMemory; packages longmemory / longmemory-sdk, with openmemory-js@2 / openmemory-py@2 as forwarding bridges). Open-source cognitive memory engine for LLMs and agents.

AI memory platform sold to telecom carriers: memory, identity and on-network inference that turn each subscriber identity on the network into an agent (products: My AI, Persona Studio, Memory Core; MODEL-4).

Long-term memory engine for developers — captures everything the user does (browser, IDE, terminal) on-device, exposes via MCP for any IDE/agent.

Pydantic-AI ships no native persistent memory; agents start fresh each run. Long-term memory typically added via third-party integration (e.g. Hindsight) using tools + auto-injected memory instructions.

Voice agents. Short-term context within call native; long-term memory via webhook integration to CRM / external DB. Cross-agent memory sharing in multi-agent setups.

Hugging Face barebones agent framework. Memory lives as a Python list; no built-in persistence. Step callbacks let you mutate memory between steps. Persistence is left to the user — community proposals exist for "memory bank"-style addit…

Acquired by Asana (completed 2026-05-28); continues as its own product and brand. Connects enterprise knowledge sources (SharePoint, Confluence, Notion, Drive, DBs) as memory layer with access controls, versioning, citations. Agents quer…

AWS code-first agent framework. Multi-LLM (Bedrock, Anthropic, Gemini, OpenAI). Memory via Mem0 integration (ElastiCache for Valkey + Neptune Analytics) or Bedrock AgentCore Memory. Local default uses FAISS; OpenSearch for production.

Superseded: the sweepai/sweep README says the team now builds an AI coding assistant for JetBrains; the GitHub-app product described here is no longer the focus (repo not archived). No dedicated persistent memory layer. Operates as a Git…

Enterprise Context Engine builds a multi-dimensional knowledge graph from repos + CI/CD + PRs + tickets + docs at the org level. Individual completions stay session-scoped. Tabnine Agents (Nov 2025) adds team-shared agent context. Acquir…

YC S25 + $3M seed (Feb 2026). Workflow orchestration mapping corporate environments as a structured context graph so agents always have institutional knowledge for tasks. CTO frames differentiator as "context engineering."

Voice agents. Externalises memory from LLM into structured call state — variables rather than model recall — reducing hallucinations. Squad mode passes context across multi-agent assistant hand-offs in same call.

Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as c…

dspy.History primitive — typed field holding messages: list[dict] that slots into any Signature . No persistent memory of its own; purely a structured context-injection contract. DSPy's optimisation loop (MIPRO, BootstrapFewShot) treats …