dsh-rigorquant：面向经验/计算数学研究的 DSH 会话级研究插件
dsh-rigorquant 是 DeepSeek Harness (DSH) 的一个 MIT 许可插件，旨在通过上下文隔离的多智能体协作，优化经验/计算数学的长程研究流程。它解决假设提出、探索、验证与实现混杂的问题，将单次会话组织为带有边界、分工及前置检查的研究实验室。 其核心机制包括并行探索、独立重推分析形式与界限、通过反例对抗淘汰无效路径，以及由 meta-validator `rq_check.py` 进行的证据校验，拒绝无证据的通过结论。插件引入“实现前四项检查电池”，确保数值实现前有充分证据。针对随机性工作，采用固定种子和大数定律约定，并提供可选的 Jacobian MCP 升级路
Read More《Cursor Docs》-Terminal
Cursor runs shell commands directly in your terminal. Your Run Mode controls when commands run, when Cursor asks, and when terminal commands enter the sandbox.
Read More《Cursor Docs》-Canvases
Canvases let Cursor create interactive artifacts that render next to the chat. Instead of scrolling through a long markdown table or code block, you get a standalone view, laid out with sections, stats, and tables, that you can reopen, edit, and iterate on.
Read More《Cursor Docs》-Browser
Agent can control a web browser to test applications, audit accessibility, convert designs into code, and more. With full access to console logs and network traffic, Agent can debug issues and automate comprehensive testing workflows.
Read More《Cursor Docs》-Run Modes
Run Modes control how the Cursor agent runs tool calls, and when Cursor interrupts you for approval.
Read More《Cursor Docs》-Agent Security
AI can behave unexpectedly due to prompt injection, hallucinations, and other issues. We protect users with guardrails that limit what agents can do. By default, sensitive actions require your manual approval. This document explains our guardrails and what they mean for you.
Read More《Cursor Docs》-Prompting agents
Direct Agent with text prompts in the chat input. You can attach context, images, and voice, and switch models at any point.
Read More《Cursor Docs》-Plan Mode
Plan Mode creates detailed implementation plans before writing any code. Agent researches your codebase, asks clarifying questions, and generates a reviewable plan you can edit before building.
Read More《Cursor Docs》-Cursor Agent
Agent is Cursor's assistant that can complete complex coding tasks independently, run terminal commands, and edit code. Access in sidepane with Cmd+I.
Read More《Cursor Docs》-Design Mode
Design Mode lets you direct agents with visual prompts. From the browser in the Agents Window, you can click an element, draw on the page, or describe a change by voice. Cursor captures the context it needs and edits the code while you move on to the next change.
Read More《Cursor Docs》-Debug Mode
Debug Mode helps you find root causes and fix tricky bugs that are hard to reproduce or understand. Instead of immediately writing code, the agent generates hypotheses, adds log statements, and uses runtime information to pinpoint the exact issue before making a targeted fix.
Read More《Cursor Docs》-Agents Window
The Agents Window is Cursor's agent first interface. It provides a unified workspace to build with agents across repos and environments, including local, cloud, remote SSH, and more. It combines the power of parallel agents with the depth and control of a development environment.
Read More《Cursor Docs》-Agent Review
Agent Review runs a dedicated code review on your local changes from inside Cursor.
Read MoreDSH Noema: Installing Viewable Long-Term Memory for DeepSeek Harness
dsh-noema is a Noema long-term memory plugin developed by ZSeven-W for DSH. It integrates local-first, non-vector memory into Agents, providing noema_* tools such as recall, retrieval, and import, along with a web-based settings page. Memories are stored in Markdown format in the ~/.agent-memory directory and can be migrated from tools like Cursor, Claude Code, and Codex, with support for service keep-alive. This article introduces its positioning, features, installation commands, and usage considerations.
Read MoreIntegrating AnySearch into DeepSeek Harness: Native Web Search and Vertical Retrieval in One Step
@anysearch/anysearch-dsh is a web tool plugin developed by the anysearch-team for DeepSeek Harness, integrating AnySearch into DSH's web profile. After installation, the Agent continues to use the native `web_search` and `web_fetch` functions to access real-time web search, URL content cleaning, as well as advanced capabilities such as vertical retrieval and batch concurrent processing. It supports anonymous usage without an API key, and credentials can be configured for higher quotas. This article introduces the plugin's positioning, environment requirements, installation commands, key configuration, and typical query examples, while also noting that the plugin operates with DSH process permissions and advising users to verify the source code and license before installation.
Read MoreTurn DeepSeek Harness "Everything is Plugin" into a Runnable Chinese Course Using dsh-harness-tutorial
dsh-harness-tutorial is an MIT open-source Chinese tutorial maintained by yanhua1010, which breaks down DeepSeek Harness's "everything is a plugin" concept into a VitePress site, 8 runnable demos locked at version 0.1.0-rc.6, and a teaching-oriented mini-harness (React + Node.js TypeScript). Although categorized under "Tools and Capabilities" in community directories, the repository itself serves as educational material rather than a runtime capability plugin. This article verifies the directory page and GitHub repository to explain what it is, how to read the four lessons, how to run the demos locally, and how to complete the final project.
Read MoreY Combinator Open-Sources QM: Company-Grade Multi-Person Collaborative Agent Workspace
On July 31, 2026, Y Combinator open-sourced its internal multi-agent framework QM (Quartermaster) under the MIT license, and it quickly gained over 10,000 stars on GitHub. QM is a work-agent infrastructure for entire companies, supporting both Slack and Web terminals. Each employee and channel has isolated memory, sandboxes and permissions, and can switch Harness among Pi, OpenCode, Codex and Claude Code. This article sorts out its architecture, Strict/Auto/Dangerous security policies and qm init self-hosted deployment method, for teams evaluating enterprise-level agent operating systems for reference.
Read MoreThe Two AI Coding Powerhouses in 2026: How Claude Code and Cursor Will Divide Labor
In 2026, a new consensus has formed in the developer community: Claude Code (terminal Agent + Claude Agent SDK) and Cursor (AI IDE) are often used in combination rather than being an either-or choice. Based on official documentation from Anthropic and Cursor, as well as public reviews from Faros.ai, FutureProofing.dev and other sources, this paper compares the differences between the two tools in terms of MCP integration, subagents orchestration, multi-model routing, Bugbot review and token efficiency, proposes a practical division of labor scheme such as "Cursor for daily coding, Claude Code for cross-file refactoring and CI automation", and explains that Claude Code can coexist as an extension of Cursor.
Read MoreMajor Version Update of MCP: Stateless Core, Official Extensions and Enterprise-level Certification
On July 28, 2026, the Model Context Protocol released its 2026-07-28 specification, marking the largest revision since the protocol's launch. The core changes include: shifting from a bidirectional stateful protocol to a request/response stateless model, removing the initialize handshake and Mcp-Session-Id; upgrading MCP Apps and Tasks to official extensions; and strengthening OAuth 2.0/OIDC authentication to integrate with enterprise IdPs. With monthly SDK downloads exceeding 400 million and over 950 Claude connectors, MCP is becoming the de facto standard for Agent interconnection.
Read MoreGPT-5.6 Luna's Price Cut Twice: How OpenAI Cut Agent Reasoning Cost to $0.2 per Million Tokens
On July 30, 2026, OpenAI announced an 80% cut in the input pricing of GPT-5.6 Luna API to $0.2 per million tokens, a 20% reduction for Terra, and no change for Sol. This move came less than three weeks after the general availability of the three-tier models on July 9, reflecting the intensifying AI inference cost war. This article sorts out the new pricing lists for Sol, Terra and Luna, the changes to Prompt Caching and Codex quotas, as well as selection suggestions for cost-sensitive Agent workloads.
Read MoreMCP's Largest-Ever Update: Stateless Core Shift on 2026-07-28, Agent Infrastructure Goes Enterprise-Grade
On July 28, 2026, the Model Context Protocol released its 2026-07-28 specification: the core of the protocol has shifted from a bidirectional stateful model to a stateless request/response architecture, the initialize handshake and Mcp-Session-Id have been deprecated, and it now supports any instance handling requests after load balancing. It simultaneously introduces MRTR multi-turn interaction, Mcp-Method/Mcp-Name header routing, and list response cache hints, and graduates MCP Apps, Tasks and enterprise managed authorization to official extensions. OAuth hardening includes RFC 9207 iss verification and DCR migration to CIMD. The monthly downloads of Tier 1 SDKs are nearly 500 million, and companies such as Anthropic and Google Cloud have stated that this is a key step toward the productionization of Agents.
Read MoreOrca: An ADE Running Five Coding Agents Simultaneously, A New Parallel Orchestration Paradigm with Over 20,000 Stars on GitHub
Orca, an open-source project by Stably AI, was a trending ADE (Agent Development Environment) on GitHub Trending in July 2026. Built on Git Worktree, it provides isolated parallel runtime environments for over 30 CLI Agents including Claude Code, Codex, and OpenCode. It supports one-click Worktree creation from GitHub/Linear tasks, UI context injection via Design Mode point-and-click, as well as SSH remote Worktree. Its GitHub stars exceeded 20,000 in July and continued to rise. This article sorts out the differences between ADE and traditional IDEs, core mechanisms, installation methods and applicable scenarios, to help evaluate multi-agent parallel development solutions.
Read MoreMoonshot Open-Source Kimi K3: An Open-Source Cutting-Edge Model with 2.8T Parameter MoE, 104B Activations and 1M Context Window
On July 27, 2026, Moonshot AI released the full weights of Kimi K3 on Hugging Face and GitHub: a 2.8T total parameter MoE model with 16 activated experts out of 896, 104B activated parameters, 1 million token context window, and native multimodal capabilities. Based on the official README and arXiv technical report, this paper sorts out the key points of the KDA and Stable LatentMoE architectures, interprets the differences between Agent evaluations such as Terminal-Bench and model harness tests, and introduces the API, deployment paths via vLLM/SGLang, and the usage boundaries of the Kimi K3 License.
Read MoreCopilot Connects to Grok 4.5 and Claude Opus 5 in July, IDE Becomes a Battlefield for Agent Model Selection
On July 24 and 28, 2026, GitHub's official Changelog consecutively announced that Claude Opus 5 and Grok 4.5 have been integrated into GitHub Copilot, and users can switch between them via the model selector in VS Code, Copilot CLI, JetBrains and other entry points. Opus 5 is designed for complex long-chain Agent tasks, while Grok 4.5 boasts a maximum context window of 500,000 tokens and parallel tool calling. For Business/Enterprise plans, the feature requires administrators to enable the relevant policy, and Grok 4.5 is disabled by default. This article sorts out the access scope, plan differences, billing methods and selection references based on the official announcements.
Read MoreOmniRoute Sees Over 9,000 Star Gains in a Week: Unifies 290+ Model Providers via Local AI Gateway
OmniRoute (diegosouzapw/OmniRoute) is one of the open source projects with the fastest growth in stars in the GitHub AI Agent category in July 2026, with an increase of approximately +9,200 in 7 days. This MIT-licensed local AI gateway aggregates over 290 model providers (including over 90 free tiers) through a single OpenAI-compatible endpoint, with built-in Combo automatic fallback, quota-aware routing, cost telemetry, and support for MCP/A2A. It can connect to programming agents such as Claude Code, Cursor and Codex. This article introduces the pain points of multi-model switching it solves, the core routing mechanism, quick start steps, as well as the security and trust boundaries during deployment.
Read More