Write code from specifications.
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
Context-budgeted visual feedback for coding agents. MCP server + CLI + Claude Code plugin that lets an agent see the UI it just changed without flooding context.
Travel platform for coding agents: hotels, tours, bookings, 13 AI experts. 21 tools, stdio.
本地化终端 AI 编程 Agent（s-code）—— 独立、架构透明同类替代品
The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.
Pi-native agent kit: extensions, skills, themes, prompts, and agents for pi-coding-agent
Model Context Protocol server for Cursor Cloud Agents API - programmatically create, manage, and interact with AI-powered coding agents through MCP stdio transport. Integrate automated code generation, repository management, and agent workflows into your
Persistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.
A Pi extension that provides automated, language-aware code review after the agent writes or modifies files.
Detect any website's tech stack, DNS and email security from your terminal or a coding agent. CLI for the TechSpy API.
Local Markdown documentation hub with a built-in MCP server — coding agents create ADRs, draw diagrams and detect drift while you code.
MCP server for Bystep — lets Claude Code, Cursor and other MCP clients fetch the PRD and work through plan tasks one at a time.
MCP server that gives AI agents LightningChart JS Trader source-of-truth guidance.
One-command installer that sets up the complete Grubtech Integration Agent (MCP server + AI agent personas) for Claude Code to help developers build restaurant and POS integrations.
MCP server — convert dashboard images to dashcraft-core React code
Local-first MCP memory and code intelligence that helps coding agents recall repo context, decisions, failures, and review impact.
A minimal, opinionated set of coding tools for driving an LLM agent over a workspace — read/write/edit/patch/move, batch read, grep/glob/diff, project-wide regex replace, bash + background monitors, and tree-sitter-powered outline/check_syntax — usable as
Experimental Model Context Protocol (MCP) server for VS Code integration with development tools, secure command execution, and AI-powered coding assistance. Still in active development.
ContextOS Execution Layer and MCP Server
File-bound rules for coding agents. Pin a constraint to the paths it is about; it lives in git, survives session end and tool switches, and re-checks itself. Measured: agents followed pinned rules 18/20 times versus 0/20 without.