DeepSeek Harness (dsh) 从 0 到 1 深度手册:安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比(中文 + 英文 PDF)
- dsh-plugin
- deepseek
- deepseek-ai
- agent
111,820 visible repositories in the index
2,113–2,136 of 2,904 · Most stars
DeepSeek Harness (dsh) 从 0 到 1 深度手册:安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比(中文 + 英文 PDF)
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
An Automatic Prompt Optimization Framework for Large Language Models
A power-user toolkit for ChatGPT Web — full and selective conversation export, PNG long-image export, deep-history search, timeline navigation, prompt management, folders, and LaTeX copy.
The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
dsh-Openwrite:OpenWrite 的 DeepSeek Harness 小说创作插件,含统一创作 Agent、56 个小说工具、原生工作台与标准审稿 DAG
A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时:快速开发、验证和恢复复杂 AI 工作流,并将其稳定交付为服务。
A Survey on Large Language Model-Based Game Agents (ACM CSUR)
开源的每日 arXiv / OpenReview 论文推荐与 AI 阅读平台,支持 GitHub Actions 自动更新、GitHub Pages 部署与论文问答。
FigmaChain is a set of Python scripts that generate HTML/CSS code based on Figma designs. Using OpenAI's GPT-3 model, FigmaChain enables developers to quickly generate HTML/CSS code from a Figma design input. It also includes a Streamlit-based chatbot interface for interactive code generation.
A throughput-oriented high-performance serving framework for LLMs
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型,实现了包括LLaMA,ChatGLM,BLOOM,GPT2,Seq2Seq,BART,T5,UDA等模型的训练和预测,开箱即用。
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Awesome Machine Unlearning (A Survey of Machine Unlearning)
An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型,GPU部署,数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM
AI 应用开发、Agent开发、RAG开发、FDE开发岗位面试宝典 - 二狗子整理
🐨 The cloud for your team's agents. Save your agent memory, credentials, code, and automations, portable across every agent with Kody.
OpenEverest is an open-source platform for automated database, storage and LLMs provisioning and management. It supports multiple technologies and can be hosted on any Kubernetes infrastructure, in the cloud or on-premises.
Published in CNCF Landscape: A MCP server for Kubernetes.
An open-source AI based digital marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analytics - grounded in brand context, human approval, and verifiable outputs. Best for Brands, Agencies and one person campanies.
Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A
Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.