Tag

MLX LM

Runs and fine-tunes LLMs locally on Apple silicon via the MLX framework, pulling thousands of Hugging Face models with one command. Adds 4- and 8-bit quantization, LoRA and full fine-tuning, prompt caching, and distributed inference across Macs.

NVIDIA Dynamo

Splits LLM inference into separate prefill and decode GPU pools, then routes requests with KV-cache awareness to cut redundant recomputation. Reports up to 30x throughput on DeepSeek-R1 (GB200 NVL72) and works across TensorRT-LLM, vLLM, and SGLang.

ContextForge

Federates MCP, A2A, and REST/gRPC backends behind a single gateway endpoint with centralized discovery, governance, and observability; optimizes agent and tool calling. Includes gRPC→MCP translation, plugin extensibility, OpenTelemetry tracing, and Kubernetes-ready deployment.

DeepCode: Open Agentic Coding

Transforms research papers, natural-language specs, and technical descriptions into runnable code via a multi-agent system. Covers Paper2Code, Text2Web, and Text2Backend; scores 75.9% on OpenAI's PaperBench, ahead of top ML PhDs.

Models.dev

Provides a community-curated database of AI model metadata—specs, pricing, and capabilities—and exposes it via a JSON API and a TOML-based contributor workflow for programmatic lookup and integration.

stable-worldmodel

Provides a unified Python interface to collect data, train visual/dynamics world models, and evaluate them with model-predictive control across many standardized environments. Includes reference baselines, planning solvers, dataset converters, and LanceDB-backed formats for reproducible experiments. Best suited for researchers benchmarking world-model algorithms.

AngelSlim

Model-compression toolkit for large LLMs/VLMs that integrates quantization (FP8/INT4/etc.), speculative decoding, token pruning and deployment hooks—designed for end-to-end performance on single/multi-GPU inference workflows and research-to-prod model optimization.

Archestra

Centralized enterprise platform to manage org-wide MCP servers with a private MCP registry, security guardrails, cost controls, and observability. Offers a Kubernetes-native orchestrator, built-in RAG knowledge base, security sub-agents, and tools for governed AI adoption.

Wegent

Composes AI agent teams from a Ghost+Shell+Model formula: each Bot pairs a prompt/MCP/Skills Ghost with a Chat, ClaudeCode, or Dify shell and a model like Claude or DeepSeek. Bots form Teams that run as traceable Tasks, wired to GitHub and DingTalk.

vllm-omni

Extends vLLM beyond text to serve omni-modal models — Qwen3-Omni, TTS like CosyVoice3, and diffusion image/video/audio generators — in one engine, adding the non-autoregressive Diffusion Transformer support the core project never targeted.

DeepScientist

Turns papers, repositories, or natural-language research goals into local-first executable 'quests' that automate reproducible experiments, branching, and result-to-paper workflows. Preserves experiment history, supports web/TUI/connectors, and keeps human takeover and inspection simple.

ML Intern

Drives an LLM-powered agent to autonomously research, write, and ship ML code by accessing Hugging Face docs, datasets, repos, and cloud compute. Provides interactive CLI and headless modes, approval gates, tool routing, and integrations for HF, GitHub, and Anthropic models.