潜力新星（90天）

Learn how to diagnose and apply different retrieval methods for different purposes with Pinecone.

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

nvtop for vLLM — an interactive terminal dashboard for vLLM serving performance (concurrency, throughput, cache & KV memory, latency, spec-decode, GPU)

Vision-Language Models on AMD GPUs — LLaVA, MiniGPT-4, Idefics on ROCm 🚀

Single-agent multi-modal system for insurance damage claim verification. #1 globally, HackerRank Orchestrate June 2026 (15,295 registrants). Anthropic, OpenAI, Groq, and Gemini support with a deterministic safety gate

Tencent Hy3 295B MoE (NVFP4) on 2x NVIDIA DGX Spark — TP2 over 200GbE, 256K context, 26 tok/s end-to-end. Tuned, benchmarked, agent-ready.

Qwen3.6 vLLM Toolkit — Launcher + Templates, Optimized for 2×24 GB. vLLM launcher with an optimized hybrid chat template drawing from the best community fixes for Qwen 3.6 27B.

Claude Code hook toolkit that gives vision-blind models a text description of pasted/tool-produced images.

GPU orchestrator with vLLM sleep mode

The official implement of Unified Reasoning Emotion Generalist OneEmo

GLM-5.2 QuantTrio (Unpruned ) on 4xDGX Spark (GB10): 327K-655K context or up to 5 concurrent agents, one receipe. TP4 + DCP + MTP

A standalone memory engine for AI agents in .NET, with hybrid retrieval, graph memory, pluggable providers, and behavior-shaped memories.

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's reference

Apache-2.0, model-agnostic macOS agent: bring your own model to deliver verified code, docs, slides, and computer actions.

Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.

The open-source, self-hosted alternative to NotebookLM.

MiniMax H3 全域提示词工程 Skill｜T2VA / I2VA / FL2VA / L2VA / Ref2VA｜50+ 创作玩法｜人物一致性、视频编辑、动作参考、音频控制、广告、短剧、MV、3D、数字人、Prompt 修复｜ComfyUI / RunningHub / Codex

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Phlox is a self-hostable chat platform with an agentic harness, document RAG, code execution, MCP integration and LLM gateway — running over any model provider: AWS Bedrock or any OpenAI-compatible endpoint (OpenAI, Ollama, OpenRouter, vLLM, LiteLLM, LM Studio, local models).