Agent Memory Systems: Comparative Overview

Six systems reviewed, covering the full design space: local file-based, cloud API, self-hosted infrastructure, full agent framework, and hierarchical pipeline approaches.

Quick Reference

SystemModelDeploymentLicenseStars
LinkLocal file / MCP serverLocal only
Mem0Cloud API / SDKCloud + self-hostedOpen-source55.7k
SupermemoryCloud APICloud onlyProprietary
DakeraSelf-hosted binarySelf-hosted (alpha)Open-core (MIT SDKs)
LettaAgent frameworkLocal + cloudApache-2.022.7k
TencentDBLibrary / pluginLocal (SQLite default)MIT

Architectural Approach

Each system makes a different foundational bet on where memory should live and how it should be structured.

Memory as a human-readable knowledge base. Raw sources → wiki pages → MCP query packets. Every memory is source-backed and inspectable. Agents query via MCP protocol; no cloud dependency. Best fit when auditability and data sovereignty are non-negotiable.

Signature idea: Three-layer architecture (raw → wiki → MCP packets) where provenance is first-class.

Mem0 — Cloud Memory API

Plug-in memory for any existing agent. Hybrid retrieval (semantic + BM25 + entity). ADD-only memory model — facts accumulate without deletion. April 2026 algorithm update added temporal re-ranking. Python/JS SDK makes it the lowest-friction option to adopt.

Signature idea: ADD-only accumulation with entity linking; strongest benchmark scores (91.6 LoCoMo, 94.8 LongMemEval).

Supermemory — Vector Graph API

Cloud-hosted memory with an ontology-aware graph engine — typed edges between entities, not just similarity scores. Three memory modes (Memory API, User Profiles, RAG) all sharing one context pool via containerTag scoping. Sub-300ms retrieval.

Signature idea: Ontology-aware graph edges encode why memories are related, not just that they are similar.

Dakera — Self-Hosted Single Binary

Collapses the typical 3–5-service agent memory stack into one 44MB Rust binary with built-in Candle embeddings (no OpenAI API required). Four agent-specific memory types (episodic, semantic, procedural, working) with automatic importance decay. Raft consensus clustering for horizontal scale.

Signature idea: Built-in inference via Candle — embeddings never leave the server; zero external API dependencies.

Letta — Full Agent Framework (MemGPT)

Not a memory API to bolt onto agents — it is the agent. Agents have a stable UUID, persistent core/archival/recall memory blocks, and improve continuously via sleep-time compute: background dream agents refine prompts and consolidate memories during idle time. Based on Berkeley MemGPT research.

Signature idea: Sleep-time compute — memory improvement happens asynchronously, not just at retrieval time.

TencentDB Agent Memory — Hierarchical Pipeline

Four-tier progressive abstraction: L0 raw logs → L1 atomic facts → L2 scenario patterns → L3 user persona. Short-term task context encoded as Mermaid diagrams rather than prose — compact, LLM-parseable, token-efficient. Full traceability: every persona links back to raw evidence via node_id.

Signature idea: Mermaid canvas as symbolic short-term context; lossless traceability from abstraction to raw source.


Key Design Dimensions

Memory Mutability

SystemModel
Mem0ADD-only — facts accumulate, nothing deleted
LinkEditable wiki — human in the loop
SupermemoryEvolving (Memory API handles temporal drift)
DakeraDecay — importance weight degrades over time
LettaActive management — agents read/write/search their own blocks
TencentDBProgressive abstraction — raw logs kept; higher layers synthesized

Decay (Dakera) and active self-management (Letta) are architecturally sounder for long-lived agents than ADD-only (Mem0), because stale facts eventually stop surfacing or get consolidated rather than accumulating indefinitely.

Privacy & Data Ownership

SystemData leaves your infra?
LinkNever — local only
DakeraNever — self-hosted, built-in embeddings
TencentDBNever — SQLite local default
LettaOptional — self-hosted or Letta Cloud
Mem0Yes (cloud) or optional (self-hosted server)
SupermemoryYes — cloud only

Inspectability (can a human read the stored memory?)

SystemInspectability
LinkHigh — Markdown wiki pages
TencentDBHigh — Markdown + Mermaid files at ~/.openclaw/memory-tdai/
LettaMedium — “Memory Palace” UI; structured blocks
DakeraLow — binary engine, dashboard available
Mem0Low — cloud opaque
SupermemoryLow — cloud opaque

Retrieval Strategy

SystemMethod
Mem0Semantic + BM25 + entity linking
SupermemoryVector graph (ontology-aware) + keyword
DakeraHNSW + BM25 + temporal re-ranking
TencentDBBM25 + vector + RRF fusion
LettaSemantic search over archival/recall blocks
LinkMCP query packets (agent-facing)

When to Use What

Use Link when you want a local, auditable knowledge base that human and agent can both read and edit. Best for personal/team wikis where provenance matters more than latency.

Use Mem0 when you need the fastest path to adding memory to an existing agent codebase. Best benchmark scores; Python/JS SDK; cloud handles ops. Accept the ADD-only model and cloud privacy trade-off.

Use Supermemory when relationship structure between memory items matters — the graph engine with typed edges gives richer retrieval than flat vector stores. Cloud-only, so accept the privacy trade-off.

Use Dakera when you want Mem0-like features but self-hosted and with no external API dependencies at all. Single binary simplicity is the key win; still alpha, so evaluate benchmarks independently.

Use Letta when memory should be the agent’s own responsibility, not an external service. The right choice for long-lived, personalized agents where sleep-time compute and continuous self-improvement are design goals. More opinionated — you build with Letta, not add it to an existing agent.

Use TencentDB Agent Memory when you need maximum token efficiency and full traceability in long-horizon, multi-session tasks. The Mermaid symbolic context encoding is uniquely suited to complex task pipelines (e.g., SWE-bench-style coding agents). Best choice if white-box debuggability is a requirement.


Maturity & Risk

SystemStatusRisk
Mem0ProductionLow — 55.7k stars, 319 releases, strong benchmarks
LettaProductionLow — Apache-2.0, Berkeley research provenance, 22.7k stars
LinkStableLow — local-only, no external deps
TencentDBActive devMedium — MIT + Tencent backing, but benchmarks self-reported
SupermemoryProductionMedium — cloud-only; vendor lock-in risk
DakeraPublic alphaHigh — strong claims, independent verification needed