No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by nimbalyst · MCP Server · ★ 1.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is nimbalyst safe to install? View the security audit →
Nimbalyst is the visual workspace for building with Codex and Claude Code Nimbalyst is a free, open-source, local, interactive visual editor & session/task manager for developers, product managers, designers, builders. Maximize speed, bandwidth, and context with Codex, Claude Code, Opencode (alpha), Copilot (alpha) by collaborating visually on integrated files, sessions, and tasks Iterate visually with coding agents in your markdown, mockups, diagrams, csv, Excalidraw, data models, and code. Approve the coding agent's changes in red/green WYSIWYG, edit, annotate. Manage multiple sessions in parallel and in kanban. Search, resume, link sessions to files and files to sessions. For developers we include git management, AI commit, workstreams, worktrees, and terminal. Manage tasks. Keep track of your plans, bugs, todos, etc. Have the agent edit tasks and items, add them, move them, and execute them. Humans see and edit this as well. Extend Nimbalyst. Build your own custom editors and visual interfaces integrated with the rest of Nimbalyst and your agents. Mobile app. Start, manage, and respond to your Codex and Claude Code sessions while on the go.
| Stars | 1,866 |
| Forks | 297 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 62.6510857661134/100 |
| Open Issues | 752 |
| Last Updated | 2026-10-11 |
| Created | 2025-10-30 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~16k |
These tools work well together with nimbalyst for enhanced workflows:
Looking for a nimbalyst alternative? If you're comparing nimbalyst with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget
Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity,
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen
Explore other popular mcp server tools:
nimbalyst is Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks.. It is categorized as a MCP Server with 1.9k GitHub stars.
nimbalyst is primarily written in TypeScript. It covers topics such as agentic-ai, agentic-ide, ai-agents.
You can find installation instructions and usage details in the nimbalyst GitHub repository at github.com/nimbalyst/nimbalyst. The project has 1.9k stars and 297 forks, indicating an active community.
nimbalyst is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to nimbalyst on Agent Skills Hub include ouroboros, happier, OpenContext. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: