#648 · Primary category: AI Agents & Automation
wassette
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
Project last updated:08/29/26
GitHub Stars
938
Forks
73
Contributors
22
License
MIT
Why we included this project
Giving an agent a new capability usually means trusting it with more commands. Wassette takes a different route: tools are WebAssembly components served over the Model Context Protocol, and each one runs inside the Wasmtime sandbox, so a coding assistant like Claude Code or Copilot CLI can pick up a capability on demand without ever escaping that boundary. Components ship as packaged, permissioned units with their own access rules, which keeps the model limited to what the tool exposes rather than the whole machine. Since they're distributed as ordinary OCI artifacts, versioning and reuse follow the same habits teams already have for containers. The README is upfront that this is early development, so think of it as a promising prototype for tool delivery and a live test bed for the security model, not something to run in front of production agent fleets yet.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.