PGPU extends postgres with GPU acceleration

Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped…

A framework for efficient model inference with omni-modality models

Open ABI and FFI for Machine Learning Systems

JAX backend for SGL

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Open Source Oracle Compatible PostgreSQL.

[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning

A terminal for a more modern age

Nano vLLM

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

In-browser Postgres sandbox with AI assistance (formerly postgres.new)

An Open Source alternative to the Greenplum® Database

Scripts for benchmarking Qdrant with Cohere Wiki dataset

Manages Unified Access to Generative AI Services built on Envoy Gateway

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

An automated pipeline for evaluating LLMs for role-playing.

PyTorch native post-training library

DBMS Trending Data Analysis

Kimi K2 is the large language model series developed by Moonshot AI team

Common recipes to run vLLM

"RAG-Anything: All-in-One RAG Framework"

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization