#xMemory
How xMemory cuts token costs and context bloat in AI agents

Standard RAG pipelines break when enterprises try to use them for long-term, multi-session LLM agent deployments. This is an important limitation as the demand for AI assistants continues to grow. ExMemoryA new technology, developed by…
How xMemory cuts token costs and context bloat in AI agents
Standard RAG pipelines break when enterprises try to use them for long-term, multi-session LLM agent deployments. This is an important limitation as the demand for AI assistants continues to grow. ExMemoryA new technology, developed by researchers at King's College London and The Alan Turing Institute, solves this by organizing conversations into a searchable hierarchy of semantic topics. Experiments show that xMemory improves answer quality and long-range reasoning in various LLMs while cutting inference costs. According to the researchers, this reduces token usage from more than 9,000 to about 4,700 tokens per query compared to existing systems on some tasks.
cnznews.com
March 25, 2026 at 6:16 PM
the bad news is that it still fails on some weird memory alignment bull shit
February 21, 2026 at 12:44 AM
Xmemory: Benchmarking Structured AI Memory Against RAG and Hybrid RAG
Discussion | hackernews | Author: alex_petrov
Xmemory: Benchmarking Structured AI Memory Against RAG and Hybrid RAG
Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, curr...
arxiv.org
May 1, 2026 at 12:01 PM
Feed: "FinSMEs"
Published on Wednesday, March 18, 2026
xmemory Raises $4M in Pre-Seed Funding
xmemory, a London, UK-based developer of a memory layer for AI workflows, raised $4m in pre-seed funding
www.finsmes.com
March 18, 2026 at 6:42 PM
New benchmarks show xMemory slashes token usage and trims context bloat compared to MemGPT’s raw logs. Faster, leaner memory retrieval means smarter AI agents. Dive in to see the numbers! #xMemory #TokenEfficiency #MemGPT

🔗 aidailypost.com/news/xmemory...
March 25, 2026 at 5:47 PM
Xmemory: Benchmarking Structured AI Memory Against RAG and Hybrid RAG
L: https://arxiv.org/abs/2604.27906
C: https://news.ycombinator.com/item?id=47972683
posted on 2026.05.01 at 05:15:35 (c=1, p=3)
May 1, 2026 at 12:04 PM
The challenge of managing context in multi-session LLMs is significant. xMemory addresses this by optimizing data retrieval and relation mapping instead of relying solely on traditional RAG frameworks. This reduces operational overhead, allowing for dynamically adaptive agent ...
March 31, 2026 at 10:56 AM
次世代自動車を変えるSTマイクロエレクトロニクスの革新的マイコン#東京都#港区#STマイクロエレクトロニクス#自動車#次世代マイコン

STマイクロエレクトロニクスが発表した新型Stellarマイコンが自動車の未来を一変させる。xMemory技術でイノベーションを促進!
次世代自動車を変えるSTマイクロエレクトロニクスの革新的マイコン
STマイクロエレクトロニクスが発表した新型Stellarマイコンが自動車の未来を一変させる。xMemory技術でイノベーションを促進!
news.3rd-in.co.jp
April 18, 2025 at 8:22 AM
STMicroelectronics shares rise 2.14% premarket after announcing Stellar with xMemory, a new generation of extensible memory for automotive microcontrollers. $STM #AInvest #Ainvest_Wire #investor #shareholders #investors View more:
April 17, 2025 at 8:48 AM