Hermes Agent vs Microsoft Scout (2026)

Hermes Agent

by Nous Research

Microsoft Scout

by Microsoft

Pros

• ✓Self-improving learning loop with no manual upkeep: after a complex task the agent writes and refines SKILL.md files so it can reuse how it solved a problem, and the community skills library gives common workflows a starting point.
• ✓Runs on infrastructure you control with your own model keys or a local model through Ollama, so teams handling sensitive data can keep the agent, its memory and its skills on their own machines.
• ✓Large, actively maintained open-source project at 255k GitHub stars, with MCP in both directions and one memory across about 30 messaging platforms, a desktop app and Hermes Cloud.

Limitations

• –Self-hosting needs a machine or VPS, comfort with a terminal and a model API key, and configuration is file-based, while the hosted Hermes Cloud option needs Portal credits or a subscription.
• –No built-in cost controls on LLM API usage: the agent runs autonomously and will continue making API calls during scheduled tasks and multi-step workflows, so provider spending limits need watching.
• –Memory system uses character-limited files injected as a frozen snapshot at session start rather than a vector database. This keeps the system lightweight and predictable but means very large or rapidly growing memory contexts require manual curation to stay within limits.

Pros

• ✓Genuine local execution. Scout reads and writes files, runs shell commands, builds and tests, and drives a browser on the user's own machine, then acts on Microsoft 365 data in the same session. Two unattended modes extend that: Heartbeat checks in every 15 to 120 minutes and Automations run on a schedule or a trigger.
• ✓A three-tier shell permission system gives fine-grained control. Read-only commands auto-approve, write and network commands pause for approval, and destructive commands are blocked outright. Administrators can disable whole capability categories or force approval for every non-read action through Group Policy.
• ✓Model choice is inherited from GitHub Copilot rather than fixed, so an administrator decides which Microsoft, third-party and open-source models Scout may use. Scout also acts as a Model Context Protocol client, connecting out to tool servers for capability beyond Microsoft 365.

Limitations

• –Access is gated twice and both gates are administrator-controlled. The organization must be enrolled in the Frontier program, and an administrator must deploy an Intune policy and file an attestation. Every user also needs both a Microsoft 365 Copilot license and a GitHub Copilot Business or Enterprise seat, so no individual can obtain Scout without IT.
• –Scout is prerelease software. Microsoft marks the documentation prerelease and states that preview features may have restricted functionality and may not be released for general availability. Microsoft publishes no price for Scout and no Scout-specific usage rates, so total running cost cannot be established in advance.
• –There is no independent review corpus yet. Microsoft Scout has no G2 profile, so a buyer weighing it has nothing to set against Microsoft's own description of the product.