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 mertkayacs · MCP Server · ★ 87
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is reevesagents safe to install? View the security audit →
ReevesAgents GitHub: https://github.com/mertkayacs/reevesagents ReevesAgents is a free and open source workspace manager for AI CLI agents. It helps you use several vendor CLIs at the same time, without turning your local machine into a heavy platform or locking the work into one model. It is built for people who want the best parts of multiple providers while keeping the workflow economical. Put each CLI where it is strongest: ask DeepSeek to work on backend code, use Claude for product and website direction, use Codex for a design system or implementation pass, and keep Hermes agents on mail, web, search, or research tasks when those CLIs are configured for that work. ReevesAgents gives the work a shared local shape: runs, agents, tmux windows, history, a TUI, and a local Web UI. The UI is available in 9 languages: English, German, French, Spanish, Portuguese, Italian, Turkish, Simplified Chinese, and Arabic. Why ReevesAgents Use more than one CLI without losing the thread. If you already jump between Claude, Codex, DeepSeek, Hermes, OpenCode, or other
| Stars | 87 |
| Forks | 9 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 68.994028720288/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-18 |
| Created | 2026-05-04 |
| Platforms | browser, claude-code, cli, codex, mcp, node |
| Est. Tokens | ~16k |
These tools work well together with reevesagents for enhanced workflows:
Looking for a reevesagents alternative? If you're comparing reevesagents 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.
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Curs
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Bring order to your projects, environments, and day-to-day work.
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Deterministic orchestrator for 30+ CLI AI coding agents. Git worktree isolation, HMAC audit trail, MCP server
Explore other popular mcp server tools:
reevesagents is Uses only the subcriptions you have. Control different agents with agents. Free, local, workspace for AI agents. Let one agent (Claude Code, Codex, Hermes, DeepSeek, Kimi, ...) spawn and drive others . It is categorized as a MCP Server with 87 GitHub stars.
reevesagents is primarily written in TypeScript. It covers topics such as agents, ai-agents, autonomous-agents.
You can find installation instructions and usage details in the reevesagents GitHub repository at github.com/mertkayacs/reevesagents. The project has 87 stars and 9 forks, indicating an active community.
The top alternatives to reevesagents on Agent Skills Hub include sub-agents-skills, sub-agents-mcp, kindly-web-search-mcp-server. 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: