Lightweight harness-first flow toolkit for coding agents
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Link → clean text → summary.
Local-first Agent Markdown runtime, validator, browser viewer, and agent skill installer.
One CLI for all your AI coding agents - versions, config, cloud dispatch, sessions, and teams (now with first-class Grok Build CLI support)
AI-powered chat and tool execution for Open Mercato, using MCP (Model Context Protocol) for tool discovery and execution.
Fork of node-fetch-native with support for custom agents
A proxy tool that converts normal MCP servers to use lazy-loading pattern with three/four meta-tools
Wrap node-fetch to enable proxy use.
OpenCode plugin to use your Claude Max subscription via Meridian proxy
http proxy middleware for koa
Portable multi-agent harness for .agents-based skills and workflows across Antigravity, Claude Code, Codex, OpenCode, and more
MCP server that proxies all agent actions, classifies risk, enforces natural-language policies, and logs to a local SQLite audit DB with a live dashboard.
Live multi-platform AI coding session viewer — Claude Code, Cursor, Codex, OpenCode, Hermes, Antigravity
Supercharge Claude Code with semantic code intelligence. 94% fewer tool calls • 77% faster exploration • 100% local.
Relay-maintained AgentWorkforce personas for use with `agentworkforce install`.
TypeScript definitions for http-proxy
Configure llm4agents in popular AI tools and coding agents
Mock harness simulator for testing agent-mux adapters — simulates claude-code, codex, and other CLI harnesses
Process-global proxy routing for Node.js.
OpenCode plugin that connects Cursor models via API key and a local OpenAI-compatible proxy.
OpenCode plugin that connects Cursor's API to OpenCode via OAuth, model discovery, and a local OpenAI-compatible proxy.
The open-source writing surface for AI agents. Markdown-native editor with pending change review — your agent writes, you accept or reject.
Transport/proxy runtime seam for agent-mux launcher bridging