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.
Python package to access a cacophony of neuro-imaging file formats
- python
- neuroimaging
- brain-imaging
- nifti
:deciduous_tree: probably the best abstract model/admin for your tree based stuff.
[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
A stylish alternative for caching your map tiles.
A cache for AI agents to learn and replay complex behaviors.
Avellaneda-Stoikov HFT market making algorithm implementation
A Python utility library with a stdlib like feel and extra batteries. Paths, Progress, Dicts, Downloads, Caching, Hashing: ubelt makes it easy!
- utility-library
- utilities
- cross-platform
- python
Official home of genome aligner based upon notion of Cactus graphs
A decorator for caching properties in classes.
RDP Bitmap Cache parser
Cache extension for Flask
LightMirrors is a lightweight mirror server with caching capabilities that currently supports DockerHub, K8S, PyPI, PyTorch, and NPM.
MapProxy is a tile cache and WMS proxy
Persistent, stale-free, local and cross-machine caching for Python functions.
YAS3FS (Yet Another S3-backed File System) is a Filesystem in Userspace (FUSE) interface to Amazon S3. It was inspired by s3fs but rewritten from scratch to implement a distributed cache synchronized by Amazon SNS notifications. A web console is provided to easily monitor the nodes of a cluster.
WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.
:art: color field for django models with a nice color-picker in the admin.
Rate limiting using various strategies and storage backends such as redis, memcached & mongodb
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)
- adaptive-computation
- early-exiting
- kv-cache
- llm
A sophisticated LangGraph-based agent that automates financial options analysis with real-time data from Polygon.io, smart caching, persistent memory, and professional-grade analysis. Built for traders, analysts, and developers who need intelligent options data processing
- chroma-db
- fastapi
- langgraph
- options
:gear: config and manage typed extra settings using just the django admin.
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
Cache with async power
- python
- cache
- cache-control
- asycnio