A native desktop application for developing, testing, and debugging Model Context Protocol servers.

Outworked - Cozy Office for Claude Code

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP + Agent Skill.

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

A standalone BMAD module that transforms code repositories, documentation websites, and developer discourse into agentskills.io-compliant, version-pinned, provenance-backed agent skills.

Compiles AI agent traces and truns them into reusable context.

Scala code intelligence for coding agents. Zero Build Server. Zero Compilation. Just answers.

Local-first AI coding personality profiler, usage dashboard, and evidence-grounded roast.

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

Semantic Search & Call Graphs for AI Agents (100% Local)

Local AI agent web app and CLI for running tools, code, web scans, and media generation.

Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.

See how you really use AI — X-ray your AI coding sessions locally

The semantic layer for software engineering: Connect code to meaning, build on understanding

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

htop for AI coding agents — monitor token usage, costs, and workflows across Claude Code, Cursor, Kiro, Codex, and Copilot

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.

The easiest way to run multiple Claude Code sessions, each in its own container, with a dashboard to manage them all. Quick setup with battle-tested sensible defaults and skills.

Your coding agent starts every session blank. Rekal is the memory your team is missing

Mission control for Claude Code: run many sessions in parallel with multi-account isolation, transcript viewer, cost tracking, and memory dashboards. Windows + macOS (Apple Silicon).