Code Generation

MCP server that wraps OpenAI Codex app-server — start coding agents, poll their progress, and manage permissions from any MCP client

Trail's MCP server: gives your coding agent your team's tracker and the project's durable memory, scoped to the folder you have open.

Smart UI MCP Server for VS Code, Cursor, and AI IDEs. Provides Smart UI components, metadata, and Angular code generation through the Model Context Protocol with support for Azure OpenAI, OpenAI, Anthropic, Gemini, and local LLMs.

MCP file and shell tools for coding agents: bounded multi-file reads, span edits, deduplication, searchable command output, SSH/SCP, and service-log inspection.

Local-first multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode with quota-aware rotation across multiple Claude Code and Codex subscriptions.

Local-first MCP server for task tracking and coordination of autonomous AI coding agents. This package is a thin npm launcher around the platform-specific rhizome-mcp binary.

Query the Software Observatory catalog of epistemic sensors for software correctness. Built for humans and agents: every command emits JSON with --json.

Local-first product graph for AI coding agents.

MCP server that turns ChatGPT Web into a real coding agent on your own repositories: read, search, edit, build, test, git, pull requests. OAuth 2.1. No OpenAI API key.

Run several AI coding CLIs on one repo at once. Any agent (Claude Code, Cursor, Copilot, Codex, Gemini, OpenCode, Antigravity) can delegate work to any other, with path locking so they never overwrite each other, automatic failover when one hits its usage

Your AI writes code that doesn't exist. Tribunal Kit stops it. The governance layer for AI coding agents — 52 specialists, 28 parallel reviewers, 183 skills, Rust core, MCP server. Works with Cursor, VSCode, Windsurf, Claude Code, and Aider.

Distills your Claude Code / OpenCode sessions — or any text corpus you ingest — into a dated history of how its subject changed, queryable by your agent over MCP.

The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.

Local-first coding agent memory for Claude Code and OpenAI Codex

Real-time observability for AI coding agents — Claude Code & OpenCode. Track tokens, costs, tool calls, agents, MCP, sessions, quotas and orchestration locally.

Local-first CLI for importing, searching, and exposing AI conversation history to local agents.

Open-source command center for governed AI coding agents with built-in onboarding, hard gates, MCP, and shareable run receipts.

Persistent memory for agents. Corrections stick, context compounds, every session starts smarter.

The adaptive AI harness for React Native — project-aware SDLC intelligence for any agent

Local-first memory, hybrid RAG, and agent personalization for AI coding agents (OpenCode, Claude Code, Codex, Gemini CLI, Antigravity). MCP server + CLI with persistent context, document ingestion, vector + SQLite FTS5 retrieval, sync, setup, and safe uni