NERDs – Entity-centered long-term memory for LLM agents
Long-running agents struggle to attend to relevant information as context grows, and eventually hit the wall when the context window fills up. NERDs (Networked Entity Representation Documents) are Wikipedia-style entity pages that LLM agents build for themselves by reading a large corpus chunk-by-chunk. Instead of reprocessing the full text at query time, a downstream agent searches and reasons over these entity documents. The idea comes from a pattern that keeps showing up: brains, human cognition, knowledge bases, and transformer internals all organize complex information around entities…
NERDs – Entity-centered long-term memory for LLM agents launched on March 6, 2026 with 13 votes, #1,024 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
NERDs is a system that helps long-running AI agents manage large amounts of information by creating Wikipedia-style entity pages from text corpora. Instead of searching through entire documents repeatedly, agents build and maintain these entity documents during an initial reading phase, then query them for relevant information. This approach reduces token usage by approximately 90% compared to processing full context while maintaining performance on tasks involving character relationships, plot tracking, and settings across large texts.
written from the facts on this page · September 2026
From the sources
Research console for entity-centered document analysis across very-long-context corpora
In the maker’s words, at launch
Long-running agents struggle to attend to relevant information as context grows, and eventually hit the wall when the context window fills up. NERDs (Networked Entity Representation Documents) are Wikipedia-style entity pages that LLM agents build for themselves by reading a large corpus chunk-by-chunk. Instead of…
Does a similar job
all alternatives →- GBGraph-based AI for longform writing2023 · jotte.ai · ▲212
Hey everyone, I wanted to share a new tool we've created called Jotte (https://jotte.ai) which we believe can be a game-changer for AI-generated longform writing like novels and research papers. As you may know, current AI like ChatGPT and GPT-3 have a token limit of around 4000 tokens or 3000 words, which limits their effectiveness for longer writing tasks. With Jotte, we've developed a graph-based approach to summarize information and effectively give AI "unlimited" memory. Jotte remembers recent details like the meal a character ate a page ago, while avoiding getting bogged down…
A Karpathy-style LLM wiki your agents maintain (Markdown and Git)Apr 2026 · github.com · ▲260I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard. I…
YourMemoryApr 2026 · yourmemoryai.vercel.app · ▲93This is a project that I have been building for a while now, YourMemory is a solution to agentic memory which focuses on pruning of noise rather than hoarding of data. In the current state of agentic memory most of the context is stored in the form of a MD file or is derived through a RAG model where you store each and everything. Both of the solution leads to bloated context which does not optimize the usage of any tokens. In this system we only keep relevant data in our memory and prune all the unnecessary data. The relevance of a data is derived through multiple factors such as recall…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
