Long Context Python Packages

megabyte-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

ring-attention-pytorch

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

recurrent-memory-transformer-pytorch

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

infini-transformer-pytorch

Implementation of Infini-Transformer in Pytorch

tokenpack-rag

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

ringattention

Large Context Attention

perceiver-ar-pytorch

Perceiver AR

mcp-long-context-reader

An MCP server for overcoming context window limitations when processing extensive documents.

hard-needle

Semantically hard multi-needle long-context data generator. Stop testing LLMs with random-password needles.

kakeyalattice

Discrete Kakeya cover for LLM KV cache: D4/E8 nested-lattice quantisation realising a Kakeya-style tube-cover over the direction sphere. 2.4x-2.8x compression at <1% perplexity loss on Qwen3, Llama-3, DeepSeek, GLM-4, Gemma. Drop-in transformers.DynamicCache. pip install kakeyalattice.

titans-memory

PyTorch implementation of Titans: Learning to Memorize at Test Time (Behrouz, Zhong & Mirrokni, 2024)

compactbench

Open benchmark for LLM context compaction methods — measures what survives when you replace conversation history with a compacted artifact. Multi-cycle drift, hidden ranked set.

nexusquant-kv

Training-free KV cache compression via E8 lattice quantization and attention-aware token eviction

shadowkv

shadow kv cache

replm

Recursive Language Models — process arbitrarily long prompts by offloading context into a REPL and enabling symbolic recursion via sub-LLM calls

liah

Insert a Lie in a Haystack and evaluate the model's ability to detect it.