1,054 boosters for "Agent" — open source, verified from GitHub, ready to install
人脑不是硬盘，不会无差别存储所有信息。人脑会： DNA Memory 模拟这个过程，让 Agent 真正"进化"。 并且仅在有新的 写入后才执行 ，避免重复归纳同一批记忆。
agentMemory provides AI agents with a persistent, searchable knowledge management system that syncs with project documentation. Developers building agent applications benefit from centralized memory management without manual state handling.
Recall automatically searches across memory sources when users make vague references to past conversations, helping an AI assistant reconstruct context without guessing. Ideal for users who frequently reference earlier discussions and need reliable context retrieval.
"name": "@kastalien-research/thoughtbox", "packageManager": "pnpm@9.15.4", "description": "MCP server providing cognitive enhancement tools for LLM agents: structured reasoning, mental models, and literate programming notebooks",
UI Skills provides opinionated constraints and best practices for building better interfaces with AI agents, enforcing consistent use of Tailwind CSS, motion libraries, and accessibility standards. It benefits developers building Claude-powered agent interfaces who want reliable, modern UI patterns.
Agents merge language models with tools to build systems capable of reasoning about tasks, deciding which tools to suit the situation, and iteratively working toward solutions. The function provides a production-ready implementation. Agents follow a loop pattern: input flows to the model, which dec
Trade on Lighter — a ZK-rollup perpetual futures and spot exchange. Scripts live in this skill's directory. Read commands use , write commands use . Every command prints structured JSON to stdout. Errors are always in JSON as . Commands use syntax mirroring the Lighter UI (e.g. , , ).
"name": "buildable", "description": "Local product-structure compiler, compact UI/UX brain, and quality gate for your coding agent. A prompt becomes the right archetype, selected design system, runnable build-verified starter, and reviewed result while loading only the references each prompt needs."
Subagents enable deep agents to delegate work while maintaining clean context. They're useful for context quarantine and providing specialized instructions. Subagents solve the context bloat problem. When agents use tools producing large outputs (web searches, file reads, database queries), the cont
"name": "journalism-toolkit", "description": "30 specialized journalism agents for investigative reporting, fact-checking, disinformation analysis, AI content detection, foreign news de-biasing, bot & troll detection, multimedia production, and content distribution", "name": "Contributors"
gomcp provides a Go implementation of the Model Context Protocol to enable AI agents in Cursor to interact with external tools and resources through a standardized interface. Developers using Cursor who need to extend AI capabilities with custom integrations benefit from this protocol implementation.
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
Vrooli provides Cursor rules for maintaining consistent React/MUI styling and code standards in a monorepo UI package. Developers using Cursor IDE benefit from automated enforcement of project-specific linting and documentation guidelines.
"name": "espalier-engineering", "description": "Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifth", "homep
"name": "codebase-context", "description": "Pre-maps your codebase architecture, conventions, and team memory so AI agents navigate with precision instead of exploring. Local-first MCP server with AST-backed hybrid search.", "main": "./dist/lib.js",
"name": "threejs-devtools-mcp", "mcpName": "io.github.DmitriyGolub/threejs-devtools", "description": "Three.js MCP server — inspect and edit scenes, materials, shaders, lights in real time from any AI agent",
Read the user's memex before doing anything else. It is the current map of what is active, what changed, and where deeper evidence lives. Canonical memex path: 1. Read the memex already in context or call .
Clawstr is a decentralized social network built on Nostr that enables AI agents to post, interact, and transact with each other using Bitcoin payments. It benefits AI developers and agents seeking censorship-resistant, decentralized communication and economic coordination.
"description": "Pinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash commands like /quickstart to generate AGENTS.md files and initialize Python projects and /query to quickly explo
"name": "n8n-workflow-builder-mcp", "description": "MCP server for building n8n workflows", "main": "dist/index.js",
"name": "agent-reachout", "description": "Multi-provider notification plugin for Claude Code", "name": "vibe-with-me-tools",
A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed website analysis with 13+ specialized tools.
"name": "depwire-cli", "description": "Code cross-reference visualization and AI context engine for TypeScript, JavaScript, Python, Go, Rust, and C. Zero native dependencies — works on Windows, macOS, and Linux.", "depwire": "dist/index.js"
"name": "quarkus-agent", "description": "MCP server for AI coding agents to create, manage, and interact with Quarkus applications. Provides tools for project scaffolding, dev mode lifecycle, extension skills, Dev MCP proxy, and documentation search.", "url": "https://quarkus.io"
