Ross ROSS = Recommend OSS · open-source software intelligence for agents

EverMind-AI/MSA

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts. observed · 2026-08-28

github.com/EverMind-AI/MSA · homepage · Python observed · 2026-08-28

Health v2 · maintenance only

53/100

  • Activity 81
  • Release rhythm 35
  • Longevity 22

Flags: no_releases no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 308
  • days_rel: n/a
  • days_push: 119
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

3515 stars · 228 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MSA (Memory Sparse Attention) is a Python framework for end-to-end trainable sparse latent-memory attention that scales LLM context to 100M tokens with near-linear complexity. It combines document-wise RoPE, KV cache compression, and a Memory Parallel inference engine to run 100M-token inference on 2×A800 GPUs.

Use cases

  • process 100M-token contexts with an LLM
  • run needle-in-a-haystack long-context QA
  • replace RAG with an end-to-end trainable memory model
  • compress KV cache for long-context inference
  • summarize entire large corpora with an LLM
  • build agents with lifetime-scale conversation memory

When to choose

  • you need extreme long-context (tens of millions of tokens) with minimal degradation
  • you want an alternative to RAG pipelines with end-to-end differentiability
  • you have multi-GPU hardware and need near-linear training/inference complexity

When to avoid

  • you only need standard 128K–1M context lengths
  • you need a production-ready solution with broad ecosystem support
  • you require a permissively licensed dependency and license clarity matters (no license file in repo)

Facets

framework · maturity active

machine-learning llm-inference llm-training rag search-engine large-language-models deep-learning artificial-intelligence python sparse-attention long-context kv-cache-compression latent-memory transformers research retrieval-augmented-generation gpu linux

6 sources

Member repositories

RepositoryRoleHealth v2
EverMind-AI/MSAmain53

For agents

markdown · JSON · MCP: product_card(name="EverMind-AI/MSA")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem