Lists (1)
Sort Name ascending (A-Z)
Stars
An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that drafts and verifies its own tokens.
Ornith-1.5-122B (EXL3-EAQ) on one DGX Spark with TensorFold
DSH 的 A2A v1.0 双端插件:Client 发现远程 Agent 并映射为工具,Server 对外提供 JSON-RPC/SSE 端点与连接面板 | A2A v1.0 dual-mode DSH plugin: A2A client (skills as tools) + A2A server (JSON-RPC/SSE) with dashboard.
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and …
Qwen3.8 Flash Next on one DGX Spark (TensorFold)
Qwen3.8-27B on one DGX Spark (TensorFold)
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」,桌面本身也是「插件」。
Multi-Platform Package Manager for Stable Diffusion
Lightweight Image Video Action Generation Inference Framework
ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants
Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.
Baekpica / ds4
Forked from Entrpi/ds4ds4 'dfm'('독파모') Edition; CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark
A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
TinyEngine Backend Java is a Spring Boot-based RESTful API service that powers a low-code/visual development platform, enabling users to create applications through drag-and-drop interfaces, compon…
Python 3.8+ installers that support Windows Vista SP2 and Windows Server 2008 SP2
A free Python-distribution for Windows platform, including prebuilt packages for Scientific Python.
The agent that grows with you
DeepSeek Harness: Everything is a Plugin.
Reliable model swapping for any local AI server. Chosen by thousands of users. Batteries included. If we don't have it, you probably don't need it.
Docker configuration for running VLLM on dual DGX Sparks
Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.
Low-Latency Accelerated Web Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…