MCP local-first CLI tool that converts PRD text files into persistent execution graphs (SQLite) for structured agentic workflows

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Playwright-native CLI for inspecting live React apps without opening the DevTools UI.

MCP server for ntfy.sh notifications, asynchronous agent messaging, and human-in-the-loop workflows.

Beautiful, informative status line for Claude Code. Zero dependencies, cross-platform. pip install claude-status

A Codex skill that reports which skills influenced each reply and gives evidence-based suggestions on which skills to keep, observe, use on demand, or disable.

Structured code exploration for AI agents

A local-first multi-repo workspace system with shared runtime control, memory, docs, and agent tooling.

Package manager and registry for Claude skill packages - install, validate, score, and publish .skill packages with Claude Code integration via MCP

Authority-aware asset supply chain for curated OpenCode and GitHub Copilot runtimes.

Agent-first CLI for legacy Jira Server 8.13.5. Rust, single binary, TOML config, JSON output.

Structured procedure definitions for human-reviewable workflows that can be observed, authored, converted, or synthesized before runtime.

Human + agent shared task graph — React Kanban UI, MCP server, bidirectional YAML sync

Official example skillsets for Skilldex - reference implementations showing how to structure simple, medium, and complex Claude skill packages

macOS local trust broker for agent-mediated tool execution with explicit trust modes, trust-pinned wrappers, and fail-closed credential handoff.

Bootable Ubuntu image pre-loaded with LLMs, agent frameworks, and tooling - boot, SSH in, run an agent, zero setup.

CI/review monitor for the Gyre agent loop. Watches open PRs, correlates to Drydock work items, nudges coding agents on failures, and notifies Telegram when PRs are ready for review.

Seamlessly sync your Confluence workspace with local Markdown files. Built with robust validation and Git integration to power autonomous AI agents and human-driven workflows.

OpenClaw skill: PLAN mode - BUILD mode with auto-debug, auto-test, and Plan Fidelity Score.

Harness-agnostic repo conventions for AI-agent-assisted development: tickets, wiki, audit/bootstrap workflows. Works with Claude Code, Codex, Cursor, or no harness.