Prompt Injection Scanner
Scans RAG content/scraped pages for indirect prompt injection
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
Scans RAG content/scraped pages for indirect prompt injection
Scans RAG content/scraped pages for indirect prompt injection
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
Durable user/project memory for MCP clients: recall context and remember selected facts.
20 MCP tools + 48 skills for ENCODE Project genomics — search, download, pipelines
Symbol-level npm dependency analysis: scan verdicts, native alternatives, migration prompts.
Local repo context for coding assistants with semantic search and graph relationships.
Stateful Windows RPC attack-surface research for AI agents: 22 tools on NtObjectManager.
Search Fiverr gigs, sellers, pricing, and reviews. No API key required.
Compile, run and check CUDA and HIP kernels without a GPU: wrong results, races, memory errors
Multi-tenant hybrid RAG & evidence verification MCP server enforcing PostgreSQL RLS.
Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.
Search, read and edit the shards and drawings in your Netherstone vault. Needs the desktop app.
Convert .eml and .mbox email to clean Markdown for RAG, LLM pipelines, and local knowledge bases
Search open-source research papers across arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar.
Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
Check what Perplexity, Claude, ChatGPT, Gemini, and Google AI Overviews cite for any query.
Long-term, drift-free cognitive memory engine for AI Agents and Cursor IDE.
Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.
Fetch content from the web, cleaned up nicely for LLMs (using Defuddle).
Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.