Git Stars Git Stars

#long-context Repositories

Discover 21 active open source GitHub repositories tagged with #long-context, accumulating 35,835 total stars (averaging 1,706 stars per project). Leading this topic is InternLM/InternLM with 7,280 stars.

21
Total Repositories
35,835
Total Stars
1,706
Avg Stars/Repo
Programming Languages: Python JavaScript Shell
1
InternLM/InternLM

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

InternLM
โญ 7,280 Python ๐Ÿ‘ค InternLM Organization ๐Ÿ• Updated 2025-10-30 ๐Ÿ“… Created 2023-07-06
2
mit-han-lab/streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

mit-han-lab
โญ 7,165 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-07-11 ๐Ÿ“… Created 2023-09-29
3
dvlab-research/LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

JIA-Lab-research
โญ 2,696 Python ๐Ÿ‘ค JIA-Lab-research Organization ๐Ÿ• Updated 2024-08-14 ๐Ÿ“… Created 2023-09-21
4
PKU-YuanGroup/Helios

[TPAMI 2026๐Ÿ”ฅ] Helios: Real Real-Time Long Video Generation Model

PKU-YuanGroup
โญ 2,271 Python ๐Ÿ‘ค PKU-YuanGroup Organization ๐Ÿ• Updated 2026-11-01 ๐Ÿ“… Created 2026-03-02
5
THUDM/LongWriter

[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

THUDM
โญ 1,867 Python ๐Ÿ‘ค THUDM Organization ๐Ÿ• Updated 2025-06-24 ๐Ÿ“… Created 2024-08-12
6
snap-stanford/memorilla

๐Ÿฆ Memorilla: Latent Semantic Memory for LLMs

snap-stanford
โญ 1,565 Python ๐Ÿ‘ค snap-stanford Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-23
7
LilMGenius/paperthin

The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

LilMGenius
โญ 1,469 JavaScript ๐Ÿ‘ค LilMGenius User ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2026-06-19
8
peonist-ai/halogen-flash-server

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

peonist-ai
โญ 1,412 Shell ๐Ÿ‘ค peonist-ai Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-08-26
9
NVIDIA/kvpress

LLM KV cache compression made easy

NVIDIA
โญ 1,258 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2024-11-06
10
MoonshotAI/Kimi-VL

Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities

MoonshotAI
โญ 1,203 ๐Ÿ‘ค MoonshotAI Organization ๐Ÿ• Updated 2025-07-15 ๐Ÿ“… Created 2025-04-09
11
THUDM/LongBench

LongBench v2 and LongBench (ACL 25'&24')

THUDM
โญ 1,182 Python ๐Ÿ‘ค THUDM Organization ๐Ÿ• Updated 2025-01-15 ๐Ÿ“… Created 2023-07-29
12
ARahim3/kaggle-tpu-lab

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

ARahim3
โญ 812 Python ๐Ÿ‘ค ARahim3 User ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2026-08-31
13
canarybyte/veridrop

Online checker: veridrop.app | AI API relay checker: Claude relay checker, OpenAI relay checker, Gemini relay checker, relay authenticity verification, long-context verification, thinking-signature verification, relay red-and-black list, self-hosted and open source.

canarybyte
โญ 777 Python ๐Ÿ‘ค canarybyte User ๐Ÿ• Updated 2026-09-20 ๐Ÿ“… Created 2026-05-05
14
haoliuhl/ringattention

Large Context Attention

haoliuhl
โญ 774 Python ๐Ÿ‘ค haoliuhl User ๐Ÿ• Updated 2025-10-13 ๐Ÿ“… Created 2023-06-01
15
mem-eval-suite/LoCoMo_refined

LoCoMo Refined: Recalibrating LoCoMo with stricter LLM judging and a cleaned dataset.

mem-eval-suite
โญ 692 Python ๐Ÿ‘ค mem-eval-suite Organization ๐Ÿ• Updated 2026-05-18 ๐Ÿ“… Created 2026-04-11
17
lucidrains/MEGABYTE-pytorch

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

lucidrains
โญ 655 Python ๐Ÿ‘ค lucidrains User ๐Ÿ• Updated 2024-12-27 ๐Ÿ“… Created 2023-05-15
18
lucidrains/ring-attention-pytorch

Implementation of ๐Ÿ’ Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

lucidrains
โญ 547 Python ๐Ÿ‘ค lucidrains User ๐Ÿ• Updated 2025-05-16 ๐Ÿ“… Created 2024-02-14
19
MemTensor/MemT-1.0

Official repository for MemT-1.0

MemTensor
โญ 545 Python ๐Ÿ‘ค MemTensor Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-10-19
20
huawei-csl/KVarN

KVarN is a native vLLM KV-cache quantization backend for your agents: 3โ€“5ร— more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

huawei-csl
โญ 521 Python ๐Ÿ‘ค huawei-csl Organization ๐Ÿ• Updated 2026-06-22 ๐Ÿ“… Created 2026-05-29
21
THUDM/LongCite

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

THUDM
โญ 516 Python ๐Ÿ‘ค THUDM Organization ๐Ÿ• Updated 2024-12-31 ๐Ÿ“… Created 2024-08-31

Frequently Asked Questions

1

What is the most popular #long-context repository on GitHub?

The top ranked open source #long-context project on GitHub is InternLM/InternLM with 7,280 stars. Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

2

Which programming languages are most used in #long-context repositories?

Among the top ranked #long-context projects on GitHub, the most common programming languages are Python, JavaScript, Shell.

3

How is the #long-context repository ranking calculated?

We track 21 active open source repositories tagged with #long-context (500+ stars), totaling 35,835 stars with an average of 1,706 stars per repository. Rankings update daily from the GitHub API.