Die Werkzeugbeschreibungen sind auf Englisch.
RAG und Suche
Retrieval, Vektordatenbanken, Embeddings und semantische Suche.
Anwendungsfall
Aktivität
Sortieren nach
141
Werkzeug-Rangliste
Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.
- 1Aktiv
Sense
MCPCodebase understanding for AI coding agents — symbol graph, blast radius, semantic search.
mcpgemessenes WachstumQuelle öffnen ↗
35GitHub-Sterne+3 (+9.4 %) - 2Aktiv
SHM v6.10.1 — 自演化超图记忆 (CudaAccel: 本机 embedding 强制 CUDA)
githubgemessenes WachstumQuelle öffnen ↗
6GitHub-Sterne+1 (+20.0 %) - 3Aktiv
story-shot-agent
Sonstige剧本分镜工具智能体(PenShot):电影/动漫/短剧/小说/剧本→分镜→片段→prompt | 基于 LangGraph+LLM,自动解析任意格式剧本,生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致,支持 MCP/REST API/函数调用 | Python库 + A2A集成。(LLM-powered screenplay-to-video-prompt agent. Break scripts into…
githubgemessenes WachstumQuelle öffnen ↗
157GitHub-Sterne+6 (+4.0 %) - 4Aktiv
ai_osint
Skill🤖 Curated AI OSINT resources — Google dorks, Shodan queries, GitHub dorks, and techniques to discover exposed LLM endpoints, leaked AI API keys, misconfigured vector databases, and unprotected AI agents
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/7WaySecurity/ai_osint ~/.claude/skills/ai_osint159GitHub-Sterne+6 (+3.9 %) - 5Aktiv
Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.
githubgemessenes WachstumQuelle öffnen ↗
171GitHub-Sterne+6 (+3.6 %) - 6Aktiv
deja-vu
MCPSearch your past AI coding sessions — Claude Code, Codex, Cursor and 17 more. Indexes the session history they already wrote to disk, including months from before you installed it, and recalls it in any of them. No LLM, no embeddings, one…
githubgemessenes WachstumQuelle öffnen ↗
742GitHub-Sterne+11 (+1.5 %) - 7Aktiv
MindMemOS
Skillgithubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/mindscale-noah/MindMemOS ~/.claude/skills/MindMemOS970GitHub-Sterne+12 (+1.3 %) - 8Aktiv
Octocode
MCPAI-powered code indexer with semantic search and knowledge graphs
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add octocode -- npx @muvon/octocode459GitHub-Sterne+9 (+2.0 %) - 9Aktiv
Resume-Matcher
SonstigeThe #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
githubgemessenes WachstumQuelle öffnen ↗
28 316GitHub-Sterne+22 (+0.08 %) - 10Aktiv
ai-dev-stack
SkillProduction-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack10GitHub-Sterne+1 (+11.1 %) - 11Aktiv
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add obsidian-brain -- npx obsidian-brain10GitHub-Sterne+1 (+11.1 %) - 12Aktiv
LLMVault
SonstigeAn intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.
githubgemessenes WachstumQuelle öffnen ↗
311GitHub-Sterne+6 (+2.0 %) - 13Aktiv
Context Engineering: Build Consistent, Accurate, Predictable AI Systems
githubgemessenes WachstumQuelle öffnen ↗
135GitHub-Sterne+4 (+3.1 %) - 14Aktiv
MCP server for local codebase indexing, semantic search, and code dependency graphs.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add socraticode -- npx socraticode3 275GitHub-Sterne+12 (+0.37 %) - 15Aktiv
skills
SkillAgent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/qdrant/skills ~/.claude/skills/skills230GitHub-Sterne+5 (+2.2 %) - 1613GitHub-Sterne+1 (+8.3 %)
- 17Ruhend
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add agent-knowledge -- npx agent-knowledge13GitHub-Sterne+1 (+8.3 %) - 18Aktiv
llm-wiki-plugin
SkillAndrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add praneybehl/llm-wiki-plugin97GitHub-Sterne+3 (+3.2 %) - 19Aktiv
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
githubgemessenes WachstumQuelle öffnen ↗
378GitHub-Sterne+5 (+1.3 %) - 20Aktiv
Master-skill
SkillFoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/xr843/Master-skill ~/.claude/skills/Master-skill380GitHub-Sterne+5 (+1.3 %) - 21Aktiv
ratel
MCPContext engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
githubgemessenes WachstumQuelle öffnen ↗
433GitHub-Sterne+5 (+1.2 %) - 22Aktiv
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem…
githubgemessenes WachstumQuelle öffnen ↗
56GitHub-Sterne+2 (+3.7 %) - 23Aktiv
ChatCrystal
MCPLocal-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.
githubgemessenes WachstumQuelle öffnen ↗
57GitHub-Sterne+2 (+3.6 %) - 24Aktiv
databend
SonstigeData Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.
githubgemessenes WachstumQuelle öffnen ↗
9 433GitHub-Sterne+9 (+0.10 %)
Lern- und Referenzressourcen
Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.
- 1AktivQuelle öffnen ↗
🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。
githubRessourcegemessenes Wachstum14GitHub-Sterne+1 (+7.7 %)