MemoRAG
https://github.com/qhjqhj00/MemoRAG
RAG framework on top of a long-context memory model. Builds global memory once, generates contextual clues at query time. TheWebConf 2025.
At a glance
- Type
- Global memory-enhanced RAG
- Tier
- T3
- Section
- Research / specialised systems
- Created
- 2024-09
- Latest release
- v0.1.5 2024-09-24
- License
- Apache-2.0
- GitHub
- 2.2k★ Python
- Pricing
- searched not found
- Funding
- not applicable — not commercial
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- read-only
- unit
- chunk
- governance
- inspectable
- conflict
- n/a
When to use
Optimised for: research positioning (see memory_model)
Anti-fit: not applicable - research paper
Pros & cons
Pros
Extends RAG with explicit memory layer — bridges retrieval and stored facts.
Cons
Position between RAG and memory layer is muddled — neither owns the use case decisively.
Claims & capabilities
Up to 1M-token contexts (with beacon_ratio=16). 30× pre-fill speedup via caching. Encoding+chunking+indexing 200K-token context: ~35s cold, 1.5s from cache.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- searched not found
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — research paper, no deployed product
- A2A
- not applicable — research paper, no deployed product
- OpenTelemetry
- not applicable — research paper, no deployed product
Similar systems
Other research / specialised systems in the catalog, ranked by inbound references.
- A-MEM T3
Treats memories as atomic linkable notes — explicit nod to Zettelkasten knowledge management. Dynamic linking; retroactive memory revision.
- BAI-LAB MemoryOS T3
Hierarchical "OS" with Storage / Updating / Retrieval / Generation modules. Short-term → mid-term via FIFO dialogue-chain; mid-term → long-term via segmented paging.
- Titans (Google) T4
Neural long-term memory module that learns to memorise at test time. Uses gradient-of-loss as "surprise" signal; adaptive weight-decay forgetting. Three variants: MAC (memory-as-context), MAG (memory-as-gate), MAL (memory-as-layer).
- EverMemOS T4
Self-organizing memory OS for structured long-horizon reasoning. Three-phase model: episodic, semantic, reconstructive.
- EVOLVE-MEM T3
Dynamic Memory Network + Hierarchical Memory Manager + Self-Improvement Engine. L0 raw embeddings, L1 contextual summaries, L2 high-level principles. NeurIPS 2025 (Scaling Environments for Agents workshop).
- LiCoMemory T4
Lightweight hierarchical graph (CogniGraph) with entities and relations as semantic indexing layers. Incremental graph construction, fast updates, low-latency inference. Nov 2025.