gauravapiscean/agentic-kv-cache

Reproducing agentic KV-cache policy claims on real traces. 68k requests from 393 Claude Code sessions. LRU is harder to beat than the papers suggest.

Language modelsPython#kv-cache#llm-agents#llm-inference#prefix-caching#reproducibility

2.5 Steady Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

Open on Seismograph Open on GitHub

About the project

A prefix-cache simulator for LLM serving that replays real Claude Code and Mooncake traces to test whether published policies beat LRU. The author finds LRU is harder to beat than the papers claim.

Useful for

Test your own KV-cache eviction policy on real agent-session traces
Reproduce Mooncake's published hit-rate-vs-capacity curve
Measure how much recompute comes from capacity pressure rather than TTL

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

2 stars today.
The repository is 3 days old and already has 21 stars.
Hacker News: “LRU is harder to beat than the KV-cache papers suggest” — 108 points, 3 days ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 21
Stars in a day: 2
Forks: 0
Issues and pull requests: 0
Watchers: 0
Language: Python
License: MIT
Created: September 10, 2026
Last push: September 10, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

LRU is harder to beat than the KV-cache papers suggest108 points, September 10, 2026

Spotted in

September 13, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/gauravapiscean/agentic-kv-cache.svg?lang=en)](https://gitnova.dev/en/r/gauravapiscean/agentic-kv-cache)

Similar projects

6.1
JustVugg/colibri
A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

BreakoutLanguage modelsC+1,048 stars in a day
5.7
asgeirtj/system_prompts_leaks
A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message.

BreakoutLanguage modelsJavaScript+428 stars in a day
5.1
kennethwolters/litelm
A lightweight litellm alternative: routes LLM calls across 19 providers and translates message formats in ~2,900 lines with two dependencies, without proxy, caching, or cost tracking.

Early signalLanguage modelsPython+9 stars in a day
5.0
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…

Early signalLanguage modelsPython+81 stars in a day
4.8
unclecode/crawl4ai
Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

BreakoutLanguage modelsPython+411 stars in a day
4.5
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…

CoolingLanguage modelsPython+118 stars in a day