Dedicated memory layers

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

"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.

Back-office operations platform where agents and domain experts triage and resolve cases; each resolved case feeds a context graph, and a 'MemoryRank' component reuses prior successful cases to route new work.

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…

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

Reasoning-focused successor to HyperCLOVA X. Pre-trained on ~6T high-quality Korean + English tokens. 128K context via rotary position embeddings + grouped-query attention. Sovereign reasoning LLM for Korean enterprises and government.

Builds agents that learn from experience by constructing a "world model" of the micro-environment they operate in. Specialise over time through Agentic RL loop rather than relying on static prompt context. Targets the ~50% task-completio…

Cloud-free agent memory using information-geometric retrieval (Fisher-Rao distance + BM25 + entity graph + temporal fusion via 4-channel RRF) instead of LLM calls for scoring and lifecycle. Mode A is the only system to cross 70% LoCoMo w…

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.

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

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…

Agent-memory product. LLM-curated hierarchical context. Now ships as ByteRover Desktop (V4) with cloud-synced spaces for agents and teammates; the open-source CLI repo campfirein/byterover-cli is archived.

Korean startup. Connects scattered internal/external data across multiple chats and services to improve AI answer quality at retrieval. 18-year-old CEO Jang Jun-ha; pitch is that answer quality depends on what the model remembers, not wh…

Renamed ByteRover CLI (brv); repo campfirein/byterover-cli archived read-only 2026-09-27, license changed to Elastic License 2.0. Opensource memory layer focused on programming agents — works with Cursor, Windsurf, Claude Code, Roo Code …

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.

Offline since Apr 2026 (pulled from app stores and the Ola platform per press reports); Ola Krutrim's own Kruti page says (checked 2026-10-29) that Kruti AI is under maintenance and will be back shortly, with no official shutdown stateme…

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.

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

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

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

Shenzhen. Argues attaching external vector stores is architecturally flawed; trains memory as an intrinsic capability via Agentic RL. Plans B2B enterprise KM and C2C personalisation in 12 months. Founded by Tianjin University AI professo…

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

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

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…

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).

Walrus is a Sui-blockchain decentralised storage protocol; MemWal is its AI-facing SDK that stores encrypted agent memory on-chain — portable, verifiable, shareable across agent systems with no single-vendor lock-in. Targets production a…

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.

Local context/memory engine for coding agents: stores decisions, docs and agent history on-machine (SQLite + local ONNX embeddings) and serves a ranked slice per task over MCP. Open-core Apache-2.0 core with paid Pro tier.

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.

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

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."

Node.js/TypeScript-native memory layer. SQLite + local Transformers.js embeddings (~80MB model via WebAssembly). AUDN loop (Add/Update/Delete/None) resolves contradictions before write rather than at retrieval — read-after-write consiste…

'Agent Skills as a Memory Layer': an open-source skill-memory layer that stores what agents learn as agent skill files. Built by the Memobase team. The README now says Acontext is no longer maintained; the team has moved on to alook.ai.

Open-source agent 'brain' storing explicit sourced facts with corrections and withdrawals, shared across agents; built as the memory for OpenClaw/Hermes agents. author is YC CEO; listed #6 in TeleAI Awesome-Agent-Memory

Memory library/service for stateful agents that reasons over stored messages to build 'peer' representations (theory-of-mind style user models) queryable via a dialectic API; used as Hermes Agent's and OpenClaw's user-modelling backend. …

A 'memory agent' that manages other agents' memories, deciding what to keep, what conflicts, what expires and who needs to know; runs locally (Docker/Ollama) or as a free cloud. self-reported 89.8% LongMemEval / 87.1% LoCoMo

Now Memori by Memori Labs (repo moved to MemoriLabs/Memori; adds managed Memori Cloud and BYODB). SQL-native memory engine for AI agents — single library, opt-in conscious/auto modes, structured Pydantic outputs. Aims to be 'one line of …

Open-source memory system modelled on human cognition, with perception, extraction, association and forgetting stages; also offered as a hosted product. #18 in TeleAI Awesome-Agent-Memory

Lightweight agent memory system that builds a shared, file-like 'memory wiki' across sessions, agents and devices and can extract reusable skills from agent history; also offered as a hosted service (memu.pro). #9 on GitHub agent-memory …

Neo4j Labs' graph-native agent memory library (Python and TypeScript) that stores conversations, builds knowledge/context graphs and records agent reasoning traces to learn from. Also available as NAMS, a hosted memory service (memory.ne…

Open-source 'context database' from ByteDance's Volcengine that unifies agent memory, RAG knowledge and skills behind a virtual filesystem (viking:// URIs) with tiered loading and self-evolving context. #6 on GitHub agent-memory topic; l…

Redis's original open-source working + long-term memory server for agents (REST and MCP), with automatic extraction, semantic search and topic/entity tagging; also used to give Snowflake Cortex Agents persistent memory. Superseded by Red…

Tencent's team-level memory hub that turns conversations, docs and code into four reusable memory assets: chat memory, skills, an LLM-wiki and a code graph. big-tech vendor

Memory layer for AI assistants — semantic short-term and long-term memory with concept-graph linking and decay/reinforcement.