wesight
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
No outside reports on file
Wesight runs AI agents that can execute code and access your files, so use it only in isolated projects, keep your computer patched, and be careful with what code and files you work on with it.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (freestylefly/wesight)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/freestylefly/wesight ↗
About Wesight
Wesight is a desktop workspace that helps you set up and run AI coding agents like Claude Code, Codex, and others in one place. It lets you choose which AI model to use for different tasks and appears designed to make it easier to get these agents working together.
Who it’s for
Developers who want to experiment with multiple AI coding agents on their own computer without setting up each one separately. It's for people comfortable working with open-source tools and GitHub.
Alternatives
- Continue using Claude Desktop with built-in code execution: Official, simpler setup with clear security model
- GitHub Copilot in VS Code: Integrated IDE support with Microsoft's security practices
- LangChain or LlamaIndex frameworks: Lower-level tools to build custom agent setups with more control
- Local LLM runners like Ollama: Run open-source models entirely offline without cloud routing
Setup
Check these steps against the project’s own instructions before running anything.
Follow the setup steps in the project’s official README: https://github.com/freestylefly/wesight (opens external site)
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 962
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Can execute code: This tool runs AI agents that write and may execute code on your computer, so a prompt injection attack could lead to malicious commands running with your user permissions
- File system access: The agents likely need to read and write files in your workspace to function, meaning they can access and modify any files your user account can reach
- Model routing choices: You control which AI models handle requests, but misconfiguring this could send your code or prompts to unintended services
- Local data exposure: Code, prompts, and file contents processed by the agents are stored locally; if your computer is compromised, an attacker gains access to all project data
- Supply chain risk: As open-source software, it depends on dependencies that could be updated with malicious code
How to lower the risk
Least-privilege permissions
- Run Wesight with a limited user account, not as administrator
- Keep the workspace folder separate from sensitive personal data
Network isolation
- Monitor what data is sent to external AI services when routing to remote models
- Consider running it on a machine with limited network access if testing untrusted code
Monitoring
- Regularly check what files the agents have read or modified in your workspace
- Review logs to see which models were used and what commands were executed
Red flags to watch for
- Unexpected network connections or API calls to unfamiliar services
- Agents requesting permissions beyond their normal scope or asking to access system directories
Questions
How do I install Wesight?
Wesight does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/freestylefly/wesight.
Are there security reports about Wesight?
No reports found for this package in our research (last checked 2026-10-29). Wesight currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include can execute code, file system access, model routing choices.
Is Wesight actively maintained?
Wesight has 962 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/freestylefly/wesight before pinning it in production.
What are alternatives to Wesight?
Notable alternatives to Wesight include Continue using Claude Desktop with built-in code execution (Official, simpler setup with clear security model), GitHub Copilot in VS Code (Integrated IDE support with Microsoft's security practices), LangChain or LlamaIndex frameworks (Lower-level tools to build custom agent setups with more control), Local LLM runners like Ollama (Run open-source models entirely offline without cloud routing). You can also compare Wesight side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Wesight? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/freestylefly-wesight)HTML embed:
<a href="https://agentarmorhq.com/skills/freestylefly-wesight"><img src="https://agentarmorhq.com/api/badge/freestylefly-wesight" alt="AgentArmorHQ Risk Grade for Wesight" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "freestylefly-wesight"Share with your security lead
Need sign-off to use wesight? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: wesight
- **Listing URL:** https://agentarmorhq.com/skills/freestylefly-wesight
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 962 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (freestylefly/wesight)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/freestylefly/wesight
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- freestylefly
- Source code
- github.com/freestylefly/wesight
- Est. context load
- ~59 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 962 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for Wesight
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude