NAVER HyperCLOVA X THINK
https://navercorp.com/en/tech/hyperclovax
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.
At a glance
- Type
- Korean sovereign 128K reasoning LLM
- Tier
- T1
- Section
- Dedicated memory layers
- Created
- searched not found
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Enterprise only
- Funding
- NAVER corporate (1+ trillion won invested in AI over 5 years; no external VC funding)
Taxonomy
- storage
- parametric
- retrieval
- attention
- persistence
- session
- update
- read-only
- unit
- kv-token
- governance
- opaque
- conflict
- n/a
When to use
Optimised for: Korean sovereignty + 128K reasoning
Anti-fit: not optimised for non-Korean use cases
Pros & cons
Pros
Korean-first frontier model with memory features tuned to East Asian linguistic patterns.
Cons
Korean-market focus limits global relevance; documentation primarily in Korean.
Claims & capabilities
First reasoning LLM in HyperCLOVA X family. Outperforms global models on Korean benchmarks.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Managed-only
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- not documented publicly
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Similar systems
Other dedicated memory layers in the catalog, ranked by inbound references.
- Mem0 T1
Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.
- Zep & Graphiti T1
Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.
- Cognee T1
"Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.
- Hindsight (Vectorize) T1
Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.
- Memvid T2
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).
- Supermemory T1
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.