PromptBranch
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
按你想完成的任务或你使用的应用搜索,再按分类筛选。
按使用分数排序:GitHub 星标、每周下载量、最近发布情况和端点是否响应。最常用不等于最好。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.
Local-first knowledge vaults for project docs and specs. Tagged, versioned, full-text searchable.
Pixel-perfect Material (M3) data tables for your app in one prompt: Claude Code, Cursor, Codex.
Token-lean memory for AI agents: a knowledge graph searched cheaply. Drop-in for server-memory.
RAG search over Choreo Labs (formerly WSO2) docs: APIM, IS, MI, Choreo, Ballerina, via pgvector.
Animate in OpenToonz from an AI assistant: native vector levels, xsheet timing, rigs and physics.
Local job-search tracker: roles, a status machine with evidence, rules, interviews, daily reports.
Find & fetch research datasets across 21 archives, omics registries, and literature sources.
MCP server for GLPI IT service management (tickets, assets, users, knowledge base)
Zotero MCP server: local-first search, library checks, and preview-first writes for AI agents.
Local, read-only Google Search Console MCP server. Quick Connect needs no Cloud project.
Free job-search agent: finds matching jobs, applies through your AI app, tracks it all locally.
What's hot in AI right now, ranked with receipts from GitHub, HN, npm and Hugging Face.
Self-hosted SearXNG metasearch for MCP clients: 13 tools, citation refs, deep search and crawling.
Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.
Search Geneteka, the Poznań Project and BaSIA for Polish vital records; fetch archive scans.
ESLint for AI search: audits AI-crawler access, llms.txt, schema and citability.
Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup.
A content exploration toolkit that helps LLMs surface high signal, unsummarized web content.
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows.