.png&w=828&q=75)
Meet the PC Personal Voice Assistant: a local-first, voice-driven assistant that transforms how you interact with your computer. It operates as both an intelligent knowledge source and a hands-free PC controller. You can ask it to explain complex concepts, look up live information via Google Search Grounding, or perform actions on your desktop—all while it talks back to you seamlessly via AssemblyAI's real-time WebSocket pipeline. Everything core runs locally on your PC. The auth server binds only to localhost, keeps API keys secure in a local DuckDB store, and requires no complicated deployments. It intelligently catalogs your OS and installed applications, allowing it to launch real software securely by name. Beyond simple commands, the assistant features vision-guided UI automation utilizing Gemini Computer Use, enabling it to execute screenshot-decide-act-verify loops on your desktop or browser. It functions as a sophisticated planner where multi-step goals become checkpointed, resumable plans. With built-in semantic memory, an auto-reversible undo layer, on-device openWakeWord detection, and real-time barge-in support, the assistant provides a highly fluid conversational experience. Layered security features—including prompt-injection detection, a signed tool manifest, and explicit confirmation queues for dangerous commands—ensure your machine remains safe while unlocking entirely hands-free productivity.
30 Sep 2026
.png&w=828&q=75)
The Isolated Agents SDK is a powerful security framework designed to solve one of the most pressing challenges in the modern AI ecosystem: the safe execution of autonomous agents on local hardware. As AI agents gain the ability to generate and execute code, browse the web, and interact with file systems, the risk of "prompt injection" or malfunctioning logic leading to system compromise has increased significantly. Our SDK provides a "security-first" abstraction layer that automatically wraps any Python-based AI agent—whether built with LangChain, AutoGPT, or custom logic—within a rootless Podman container. This ensures that the agent operates in a completely isolated environment with zero access to the host system unless explicitly granted. Key features include: Automatic Isolation: Move from raw Python execution to a secure container with a single function call (run_agent). Granular Policies: Define strict resource limits (CPU/Memory), network whitelists (e.g., only allow access to specific LLM APIs), and read-only file system access. Seamless Serialization: Uses advanced pickling techniques to transport complex agent states into the container without requiring manual Dockerfile management. Artifact Management: Automatically collect and map generated files, logs, and data back to the host system. By bridging the gap between high-level AI orchestration and low-level system security, the Isolated Agents SDK empowers developers to build and deploy innovative AI tools with total peace of mind.
17 May 2026