Seven platforms, different strengths. Tell us what you're trying to do and we'll point you at the best fit — plus 21 head-to-head comparisons if you're deciding between two specific options. Looking for benchmark scores instead? See the benchmarks hub.
Three quick questions. Each one narrows the field. Or scroll down for the multi-criteria filter and full matrix.
Answer 4 questions. Results update instantly.
Open-source, self-hosted, model-agnostic
✓ Largest skill ecosystem of any agent platform
✗ Setup assumes comfort with a terminal
Full guide →OpenClaw fork tuned for local GPU inference
✓ Best-in-class local GPU support — vLLM, llama.cpp, Ollama first-class
✗ Requires a capable GPU (24GB+ for most useful models)
Full guide →Security-hardened OpenClaw variant for teams
✓ Skill allowlisting enforced by default — no arbitrary code
✗ Smaller available skill pool (only allowlisted)
Full guide →top-3 on OpenRouter coding (peaked #1 Apr 2026) — multi-IDE AI coding agent
✓ top-3 coding agent on OpenRouter (peaked #1 Apr 2026) (188B tokens, 22.9% share) — 500+ models at provider rates
✗ Coding-focused only; prompts traverse OpenRouter unless using direct BYO keys
Full guide →Memory-first agent with polished MCP support
✓ Cleanest MCP tool integration of any platform
✗ Smaller skill library than OpenClaw
Full guide →Anthropic's hosted agentic coding environment
✓ Zero-setup — install, sign in, go
✗ Locked to Anthropic models only
Full guide →OpenAI's consumer agent with Custom GPTs
✓ Easiest on-ramp for non-technical users
✗ No real scheduled-task or heartbeat support
Full guide →Every dimension side-by-side. Click a platform name for its full hub.
| 🦀 OpenClaw | 🐠 NemoClaw | ⚙️ IronClaw | ⚡ Kilo Code | 📬 Hermes | 🧑💻 Claude Cowork | 💬 ChatGPT |
|
|---|---|---|---|---|---|---|---|
| Pricing | Free (you pay provider costs) | Free (GPU hardware cost) | Free (self-hosted); Enterprise tier priced per seat | Free; pay model costs via OpenRouter or BYO keys | Free self-hosted; Cloud tier $15/mo | $20/mo Pro; $100/mo Max (included with Claude plans) | Free tier; Plus $23/mo; Team/Enterprise per-seat |
| License | MIT | MIT | MIT core; commercial enterprise add-ons | Apache-2.0 (CLI: MIT) | Apache 2.0 | Proprietary | Proprietary |
| Hosting | self-hosted | self-hosted | self-hosted | self-hosted (IDE extension) | self-hosted or cloud | cloud-managed | cloud-managed |
| Requires GPU | No | Yes | No | No | No | No | No |
| Open source | Yes | Yes | Yes | Yes | Yes | No | No |
| Providers | Anthropic, OpenAI, Ollama, Ollama Cloud, OpenRouter | Ollama, vLLM, llama.cpp, OpenAI-compatible locals | Anthropic, OpenAI, Azure OpenAI, Ollama | 500+ via OpenRouter; BYO API keys for any provider | Anthropic, OpenAI, Google, Ollama | Anthropic (exclusive) | OpenAI (exclusive) |
| Skill count | 53 official + 13,700+ community | Inherits OpenClaw ecosystem | Curated allowlisted subset (~200) | Orchestrator sub-agents (planner/coder/debugger built-in) | MCP-based — thousands via MCP registry | 1,200+ curated skills + plugin marketplace | 3M+ Custom GPTs (public store) |
| Primary language | TypeScript | TypeScript | TypeScript | TypeScript (VS Code ext) | Python | TypeScript (your code, any language) | N/A (prompt + Custom GPTs) |
| Time to first agent | 15 min | 45 min | 20 min | 10 min | 10 min | 3 min | 1 min |
| Ease of setup | ●●○○○ | ●●○○○ | ●●●○○ | ●●●●○ | ●●●●○ | ●●●●● | ●●●●● |
| Power / flexibility | ●●●●● | ●●●●○ | ●●●●○ | ●●●●● | ●●●●○ | ●●●●○ | ●●●○○ |
| Stability | ●●●●○ | ●●●○○ | ●●●●● | ●●●●○ | ●●●●○ | ●●●●● | ●●●●● |
| Privacy | ●●●●● | ●●●●● | ●●●●● | ●●●○○ | ●●●●○ | ●●●○○ | ●●○○○ |
| Cost control | ●●●●● | ●●●●● | ●●●●○ | ●●●●● | ●●●●● | ●●●○○ | ●●●○○ |
21 pairwise deep-dives — pick two platforms and see how they actually differ.