Stars
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
A ChatGPT-style chat template that answers from your documents and the web, with citations.
Tonbo is an embedded database for serverless and edge runtimes.
A cloud native embedded storage engine built on object storage.
Lean certificates accompanying Navier-Stokes and Euler results
High-performance single-GPU inference for selected model checkpoints and GPUs.
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
Language model tokenization at GB/s
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Apache Paimon is a lake format that enables building a Realtime Lakehouse Architecture with Flink and Spark for both streaming and batch operations.
A benchmark built to evaluate and improve agent capabilities for supporting legal work.
DFlash: Block Diffusion for Flash Speculative Decoding
Local-first desktop markdown editor
Agent skills for search, RAG, and document parsing with Mixedbread. Install with: npx skills add mixedbread-ai/skills
Terraform provider for the CloudRift platform
A lightweight, lightning-fast, in-process vector database
Patched version of Magenta-RT enabling mixing
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Using mixedbread for AI-powered search on the AIR project.
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.
Public repository of the Micro QuickJS Javascript Engine
Repository for getting started with the OfficeQA Benchmark.
The official Python SDK for the Agentica agent framework from Symbolica