🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall (keyword/vector/BM25/entity), and a memory panel. 10 model tools, MCP server, CLI.

A build playbook that turns your coding agent into the foreman of a website build. It interviews you, forces the design and scope decisions, locks a visual system, writes the build brief, then verifies, ships, and indexes the site. Claude Code plugin and Agent Skill. Markdown only, no scripts.

Self-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉

Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.

DeepSeek Harness Mobile 是一个面向 DeepSeek Harness 的原生移动端客户端。它通过 dsh-plugin-mobile-gateway 与 Harness 建立 WebSocket 连接，将工作区、会话、实时回复和 Agent 执行轨迹带到 iPhone，同时延续 DeepSeek WebUI 克制、清晰的视觉语言

Model Context Protocol server transport: serve typed procedures as MCP tools to Claude and other MCP clients, with streaming progress, list_changed and an expose policy.

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈

Enables AI clients to retrieve OpenSea collection market data through a single tool while automatically handling x402 payments for each API call.

Enables AI coding agents to save, recall, read, list, and forget plain Markdown memories shared across tools and sessions, so facts are retrieved on demand instead of being repeated.

Gives any MCP client read-only access to Hyperliquid HIP-4 outcome market data from every deployer, including order books, fair lines with their sources, rule comparisons across deployers listing the same question, and the newest listings. Also surfaces fee-adjusted edge figures and listing order so users can scan markets, price questions, and check rule consistency.

Enables CLI agents to fold source documents into a cited Markdown knowledge base using an ontology, exposing tools to list, read, search, lint, and write pages only after user approval.

Enables MCP clients to search, read, create, and link notes in a local-first Markdown vault, with indexing, backlinks, and safe writes underneath.

Enables AI coding agents to capture deliberately deferred issues in a plain-text markdown ledger, then list, status-update, and archive them across sessions. All operations are stateless stdio tools with no network or database, and the ledger remains directly readable and editable by humans.

Enables AI clients to drive local video editing projects through a CEP bridge, covering media ingest, sequence and timeline editing, effects, keyframes, captions, markers, audio, color, and exports across hundreds of discoverable tools. Ships context resources, guided prompts, and higher-level assembly workflows for agent-driven editing.

Enables local stdio MCP clients to perform Kimi Basic and Pro web searches and fetch HTTP/HTTPS pages, returning titles, URLs, snippets, dates, source authority, optional page text, or Markdown content.

An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough, and known-good markers — as a CLI and as an MCP server.

Enables querying USDA FAS Export Sales Reporting data through read-only tools, including weekly export quantities by commodity, destination country and market year, latest-week and top-destination slices, data release dates, and lookups of commodity, country, region and unit codes. Cross-references ESR's own integer codes against packaged reference lists so valid commodities and destinations are resolved before any request.

A stdio MCP server that lets AI coding assistants search, read, add, and review shared markdown notes in a team git repository, including teammate knowledge and recent work, without extra AI calls.

Provides OAuth-secured MCP tools for working with private, Git-backed Markdown knowledge bases: searching pages, reading content, ingesting new source documents, retrieving cited original files, and reviewing history or rolling back accepted pages. Every tool call is checked against each person's or agent's current wiki grant and returns source paths and Git revisions for traceability.

Enables Claude and other MCP clients to search finn.no and create, manage, and publish Torget ads from photos — preparing images (EXIF/GPS stripping, resize, HEIC), writing titles and Norwegian descriptions, suggesting category and market price, checking for duplicates, and publishing only after explicit confirmation. Read-only search, listing details, saved-search diffs, and management of your own ads are also supported through a locally stored logged-in session.