بحث

Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124 (n=500). LoCoMo R@10 94.2% / MRR 0.8278 (n=1986). BEAM-10M +33.4% over flat retrieval. PostgreSQL + pgvector. Verified via 31-row two-benchmark ablation campaign.

Pokemon Champions battle advisor MCP server

A self-hosted, containerized platform for AI agents, exposed as Capability Packs — schema-validated, one-shot JSON tools — and native MCP. The defining metric is ≥90% pack success on 7B–30B-class open-weight models, something no frontier-targeting competitor is optimizing for.

🛠️ Enhance AI agent systems with expert skills in context engineering to optimize performance and manage information effectively.

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes agent 即让其进入「这一行的资深人」模式。MIT，Python + Shell。

Supply chain risk scorer for npm and PyPI — single-maintainer CRITICAL flags before attacks happen

🚀 Enhance retrieval with REFRAG, using micro-chunking and fast indexing for optimized RAG systems that improve efficiency and effectiveness.

🍟 Enhance AI collaboration with CLAUDE.md, orchestrating Claude for efficient context retrieval and analysis using Auggie, Codex, and Gemini.

🤖 Track developer mood swings with AI-generated insights. Get updates every 8 hours for a fun take on the tech community's emotional state.

📊 Analyze and visualize Model Context Protocol (MCP) traffic with RETICLE, your Wireshark-like tool for better network insights.

Auto-updated registry of Claude Code skills, MCP servers, Cursor rules, and AI agent prompts. Refreshed every 6 hours.

🌐 Extract languages from text seamlessly using LangExtract. Simplify language detection and enhance your projects with ease and accuracy.

Your own team of Claude Code agents you can join.

Your AI's trust filter, owned by you. Rate any URL, filter your AI's sources, build transparent information markets. MCP server + REST API + Python SDK.

Automate security research workflows with structured tool-driven assessments for Claude via MCP.

Preserve reasoning chains and logical state in Claude Projects to maintain context and build project understanding across AI sessions.

Build live workshop journals with audio transcription, keyword extraction, and a searchable JupyterBook knowledge base

Tekoälytaito vanhojen suomalaisten laivojen tiedonhakuun. Agent Skill -muotoinen taito botologien apuvälineeksi.

⚡ Facilitate seamless communication and collaboration among distributed agents with real-time capabilities and intelligent routing in a scalable platform.

Analyze Russian text quality using automated checks for i18n, plural rules, and CLDR standards to ensure linguistic accuracy.

Scan your machine for installed Claude connectors and extensions to identify potential security risks.

🔍 Access local document collections with Fathom MCP, a Model Context Protocol server that enhances AI assistants through powerful file-first search capabilities.

🧠 Improve AI memory with a three-layer system that reduces retrieval failures by 60%, enhancing learning efficiency and performance.

Deliver deep research with a 5-layer Claude skill for markets, products, competitors, regulations, and opportunities

Enforce research mode in Claude Code with source citations, direct quotes, and grounded answers to cut hallucinations

Analyze your prompt history to determine your AI interaction style and behavioral patterns using local CLI tools.

Decentralized networking protocol for AI agents — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.

Extract and analyze file metadata for forensic purposes.

New collection, first skill [pda-reframing](https://github.com/emory/ASD-AuDHD-PAI-Skills/blob/main/Skills/pda-reframing/SKILL.md) can reframe requests or decisions to defeat Persistent Demand Avoidance flavors of autism spectrum disorders, or people with ADHD that struggle to Start tasks and need help aligning with a task.

Skill pack for legal teams. NDA triage, multi-party version diff, citation verifier, meeting brief, and the Friday-newsletter status synthesis pattern. Includes 10 reference docs (privilege, verification, long documents, practice areas) and 3 firm templates. Built from the public Anthropic Claude for Legal Teams webinar dataset. *By [@sboghossian](https://github.com/sboghossian)*

🐍 ☁️ 🍎 🪟 🐧 - Agent-to-agent referral network where AI agents discover, recommend, and refer users to each other. Features bilateral trust model, credit economy, and 7 MCP tools for agent registration, discovery, and referral tracking.

🐍 ☁️ 🏠 🍎 🪟 🐧 - Agent-to-agent marketplace middleware — MCP-native discovery, negotiation, and transaction between AI agents

🐍 🏠 🍎 🪩 🐧 - Central hub that aggregates tools from multiple MCP servers with unified BM25/regex search and deferred loading.

End-to-end NLP framework

Example notebooks and tutorials

Digital forensics analysis and investigation techniques.

محرك تحسين مفتوح المصدر

[](https://glama.ai/mcp/servers/elisymlabs/elisym) 📇 ☁️ 🍎 🪟 🐧 - AI agent discovery and marketplace on Nostr with Solana payments (SOL, USDC). NIP-89 discovery, NIP-90 jobs, NIP-44 v2 encryption, on-chain micropayments.

🐍 🏠 - Bridge to local Ollama LLM server. Run Llama, Mistral, Qwen and other local models through MCP.

Agentic LLM for autonomous

Open platform for language

Provides assistance with planning family history and genealogy research projects.

🐍 ☁️ - Bridge to OpenAI API. Access GPT-4, GPT-4o and other OpenAI models through MCP.

[](https://glama.ai/mcp/servers/MastadoonPrime/sylex-search) 🐍 📇 ☁️ 🍎 🪟 🐧 - Universal search engine for AI agents. Discover products, services, and businesses across every category. 10 MCP tools, zero LLM calls, millisecond responses. `npx sylex-search`

Integration framework for AI models

Autonomous LLM-based agent framework

Open-source platform for

Use Sigma detection rules to hunt for threats and analyze security events.

[](https://glama.ai/mcp/servers/entire-vc/evc-spark-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - Search and discover AI agents, skills, prompts, bundles and MCP connectors from a curated catalog of 4500+ assets.

📇 🏠 🍎 🪟 🐧 - Self-improving tool discovery for AI agents. Searches registries, installs MCP servers as subprocesses, and persists tool knowledge across sessions — no restarts needed.

📇 ☁️ 🏠 🍎

سجل خادم MCP مستضاف ذاتيًا لو

🐍 ☁️ - Bridge to Google Gemini API. Access Gemini Pro and Flash models through MCP.

📇 ☁️ 🏠 🍎 🪟 🐧 - A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

🐍 ☁️ 🏠 🍎 🪟 🐧 - Intelligent search capabilities to let every model and client use [Claude Agent Skills](https://www.anthropic.com/news/skills) like native.

📇 ☁️ 🍎 🪟 🐧 - MCP server for the Registry Broker. Discover, register, and chat with AI agents on the Hashgraph network.

Interlink and summarize related documents into knowledge networks.

Execute autonomous multi-step research using Gemini Deep Research Agent for market analysis, competitive landscaping, and literature reviews. *By [@sanjay3290](https://github.com/sanjay3290)*

Recursive research up to PhD level across any domain (science, tech, business, arts, humanities) with source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction. *By [@Anjos2](https://github.com/Anjos2)*

Safety-first agent orchestration