Agent-first framework for Cloudflare. No worker boilerplate, no wrangler wrestling.
Skills, agents, slash commands and MCP registry distributed by claude-kit
Decision-grade evals for agents: one call — selfImprove (closed loop) or analyzeRuns (observed runs) — returns a decision packet: lift CI, judge calibration, contamination check, failure clusters, cost-quality Pareto, ranked actions. The scoring and ship-
Parallel, multi-resource CLI and modular resource availability detection script
BMAD agents + Spec-Driven Development templates for the IAgentek framework
AI agent skills and subagents for Polygraph multi-repo coordination
Agent-friendly CLI for AI generation workflows.
AnoSys SDK for OpenAI Agents — automatic instrumentation and logging for OpenAI Agents SDK
ClickUp CLI for AI agents and humans
Flowchart support
Multi-agent orchestration plugin for Claude Code
Test fixtures for Mobilewright
Platform binary package for ai-wiki-toolkit (darwin-arm64).
Skillflag producer CLI reference implementation.
A self-hosted chat interface for OpenClaw AI agents
MCP server for browser automation - the only solution supporting multiple AI agents (Claude, Cursor, VS Code) simultaneously controlling your Chrome browser
Claude Desktop Talk to Figma MCP
Parallel testing with automatic dependencies
connect any ai agents to solana protocols
[](https://www.npmjs.com/package/@mcpc-tech/acp-ai-provider) [](https://jsr.io/@mcpc/acp-ai-provider)
AI engine — providers, agents, tools, streaming, middleware
Test your documentation site against the Agent-Friendly Documentation Spec
Manage AI agent configurations with profiles and providers
Interactive TUI for creating Claude Code workflows