opensquilla
OpenSquilla is an efficient AI agent that optimizes token usage and supports multiple models and platforms.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 4.6k
- Source
- mcp-github
- Repository
- github.com/opensquilla/opensquilla
Overview
OpenSquilla is a high-performance AI agent that routes each request to the most cost-effective model via local model routing. It supports persistent memory, hierarchical sandboxing, built-in web search, and on-device embedding capabilities. Suitable for CLI, Web UI, and chat channel applications. Its plugin-based provider layer seamlessly integrates with over 20 LLM providers, including OpenRouter, OpenAI, and Anthropic. Ideal for scenarios requiring efficient token utilization and enhanced intelligence density.
Capabilities
- ▪Multi-model support
- ▪Persistent memory
- ▪Hierarchical sandboxing
- ▪Built-in web search
- ▪On-device embedding
Use cases
Setup
Recommended: Quick terminal install: `uv tool install opensquilla`. See official documentation for more installation options.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I configure the API Key?
Set `OPENROUTER_API_KEY` in environment variables or configure it via the wizard during first run.
Which operating systems are supported?
Supports Windows, macOS, and Linux.
Related skills
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.