44 packages found
The missing context layer for AI-assisted refactoring
Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zer
Deterministic persistent memory for AI agents.
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
A content-addressable protocol for universal food data
Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent —
Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, Open
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own th
claude-session-continuity-mcp
Lucairn SDKs — privacy-preserving AI infrastructure clients for TypeScript, Python, Go, and an MCP server
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts,
MCP server for the full Pāli Tipiṭaka — ~444,000 segments at parity with SuttaCentral (Sutta + Vinaya + Abhidhamma). Hyb
Architectural sensor for Python codebases - keeps structure honest under AI-assisted development
Extremely fast hybrid code search for agents.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic fo
Claude Code skill for enterprise-grade TypeScript development with type-safe patterns, modern tooling, and framework int
Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots,
Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Agent Interface Discovery
The offline internet — searchable, browsable, and self-updating. A modern server for ZIM files with cross-source search,
AI-powered code search and analysis for Claude Code with advanced type extraction across 25+ languages. Lightning-fast L
An experiment in organizing Claude Code skills. Token-optimized configurations for Go, Python, Rails, and Terraform with
Partle Marketplace MCP Server — search products and stores in nearby physical stores
Yandex Tracker MCP Server with OAuth2 support
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-deman
Example implementation of MCP Streamable HTTP client/server in Python and TypeScript.
Graph-based static analysis tool
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
Complete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops
豆包搜索 MCP server — 给换了国产模型的 Claude Code 补上联网能力。字节系信源、千字正文、每月500次免费 | Agent-first web search MCP
One command turns an empty folder into a structured, TDD-driven, security-gated project for agentic coding (Python, Type
AI-native, open-source game-dev toolkit: official Godot 4.7.1 + a checksum-locked WebGPU browser backend that renders 3D
Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.
The #1 Obsidian MCP for AI memory and local document intelligence — one vault, every agent, private and cited.
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their e
How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforce
grep that returns ranked, token-budgeted code slices — built for LLMs and coding agents. CLI + Python library + MCP serv