Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
AI agent context control plane for memory, evaluation, migration, governance, and MCP integrations.
MCPLink only★ 4Few stars
costrict-plugins mirror of mksglu-context-mode-context-mode (auto-generated, do not edit)
SkillLink only★ 2Few stars
Terminal AI coding agent with zero-config setup. Supports multiple LLM providers, MCP integration, subagents, automatic context compaction, and file checkpoints. Works on Windows, macOS, Linux.
MCPLink only★ 2Few stars
Persistent-memory Agent Skill and MCP server for resumable autonomous agent loops, context compaction, and self-healing workflows.
MCPLink onlyFew stars
SkillLink only★ 33
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
MCPLink only★ 32k
MCPLink only★ 1Few stars
MCPLink onlyFew stars
Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.
MCPLink only★ 48
Local-first checkpoints and crystals for long-running AI coding agent sessions.
SkillLink only★ 7
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, mor
MCPLink only★ 66
Local-first project memory, context packs, backlog, and verification workflows for coding agents
MCPLink only★ 4Few stars
Context Builder is a Model Context Protocol (MCP) server designed to help AI agents understand your codebase.
MCPLink onlyFew stars
Geospatial Context is an MCP server that provides agents with reverse geocoding, nearby OpenStreetMap features, and a compact sourced location analysis.
MCPLink only★ 1Few stars
mcp-omni-context: universal vision & file processor MCP server — OCR screenshots, read code files, and dump zip archives as clean LLM-ready context for non-vision models (DeepSeek V4 Flash, etc.)
MCPLink only★ 3Few stars
Resolve file-based context for AI agent DAG workflows with token budgets, zero dependencies.
SkillLink onlyFew stars
TypeScript implementation of Agentic Context Engineering — evolve your AI playbook (Bun/Node)
MCPLink onlyFew stars
Fork of claude-context-mode with LRU cache, semantic search, and persistent cross-session knowledge store
SkillLink only★ 1Few stars
A MCP server for sharing context files between AI assistants
MCPLink only★ 3Few stars
面向编码智能体的本地优先、跨会话项目上下文与记忆服务,支持增量索引、代码关系图、任务检查点和 MCP 集成。
MCPLink only★ 8
Lint your AI context files. Checks CLAUDE.md, AGENTS.md, .cursorrules, and others for dead paths, missing dependencies, stale commands, and cross-file conflicts. Optional AI-powered semantic checks. D
SkillLink only★ 4Few stars
A comprehensive Model Context Protocol (MCP) server that bridges Figma designs with AI development workflows. It provides 30 specialized tools for extracting pixel-perfect code, assets, and component
MCPLink only★ 40
Context Engineering Middleware for Claude Code — intelligent codebase indexing, token-efficient file selection, and session persistence via local MD files
SkillLink only★ 3Few stars
MCP proxy that lazy-loads tool schemas to reduce context token overhead by 4-32x
MCPLink only★ 1Few stars
Who stands behind it