Claude Find
Pull Deep Memory from across your Claude Code Sessions — when you need it.
从 GitHub 安装到你自己电脑上的开源程序。可查看星标、每周下载量和正在走红的项目。
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。 批量发布且没有任何星标的发布者不在此标签中,可在“全部”中搜索到。
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
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.
Manage Google Tasks via MCP: list, search, create, update, move, and clear tasks.
HEOR MCP server: literature search, CEA, BIA, NMA/MAIC, HTA dossiers (NICE/FDA/EMA/JCA).
Let AI agents interact with debug probes — connect, flash, read/write memory, and reset.
Search and query HackTricks pentesting documentation with quick lookup and section extraction
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Search your local Claude Code archive. For continuous capture, use the Rootz Archive plugin.
Local-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
52 tools for Claude Desktop: filesystem, knowledge graph and code search. Runs locally. Free, MIT.
Multi-engine web search with RRF fusion and Jina reranking, plus a tiered fetcher.
Retirement dates and replacements for OpenAI, Anthropic, Google and 5 more, plus Bedrock and Azure.
Knowledge graph memory for agents: every fact cites its evidence. Self-hosted, one Rust binary.
Sub-millisecond reversible PII & secret anonymizer in Rust for LLMs, agents, and MCP
500+ short, sourced fun facts: random fact, fact of the day, search and facts by topic.
A personality, mood and memory layer for AI agents, plus exact plans under hard rules. Offline.
Offline developer journal with local-LLM digests, semantic search, and MCP server.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Local MCP server: web search, cited answers, fact-checking and routed inference. No API key.