agentrq
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.
No outside reports on file
This tool is only as safe as your own server setup and how carefully you configure permissions—it's a powerful tool with real risks if misconfigured or if your infrastructure is weak.
Based on public adoption and transparency signals as of Oct 22, 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
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (agentrq/agentrq)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/agentrq/agentrq ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Agentrq
AgentRQ is a task management system that lets you control AI agents in real-time through chat on mobile, web, or desktop. It's self-hosted (runs on your own server) and works with Claude or other AI tools that support a standard called ACP.
Who it’s for
Developers and teams who want to manage AI agents themselves without relying on third-party platforms. People who prefer running their own servers and controlling their AI subscriptions.
Alternatives
- n8n: Visual workflow automation platform with AI integrations (self-hosted option available).
- Zapier: Cloud-based automation tool for connecting apps (less control, easier setup).
- LangChain agents: Open-source framework for building custom AI agent workflows in Python.
- Anthropic's Claude API with custom scripts: Build your own agent system directly using Claude's API.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on GitHub. The project appears to be self-hosted software; installation steps should be in the repository documentation at https://github.com/agentrq/agentrq (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
- 1.2k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Access to Claude API: If you connect your Claude subscription, the system can use your API key to make requests, potentially running up costs or exposing your key if the software has security gaps.
- Chat history storage: Conversations are stored on your server; if the server is breached or misconfigured, chat data could leak.
- Agent control: AI agents given task-running permissions could perform unintended actions if the system is tricked or misconfigured.
- Web interface vulnerabilities: Like any web app, it could have bugs that let attackers inject commands or steal session tokens.
- Prompt injection: Attackers could craft chat messages designed to trick the AI into ignoring safety rules or revealing sensitive info.
How to lower the risk
Least-privilege permissions
- Only give AI agents permission to access tasks they actually need.
- Never hardcode API keys; use environment variables.
Network isolation
- Run on a private network or use strong authentication (not open to the internet).
- Restrict which IPs or users can connect to the dashboard.
Monitoring
- Review logs of what tasks agents performed and what API calls were made.
- Set up alerts for unusual activity or failed API requests.
Red flags to watch for
- Unusual API costs or request patterns from your Claude subscription.
- Error messages or logs you don't understand (research them).
- People with access who shouldn't have it.
Questions
How do I install Agentrq?
Agentrq does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/agentrq/agentrq.
Are there security reports about Agentrq?
No reports found for this package in our research (last checked 2026-10-30). Agentrq currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include access to claude api, chat history storage, agent control.
Is Agentrq actively maintained?
Agentrq has 1.2k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/agentrq/agentrq before pinning it in production.
What are alternatives to Agentrq?
Notable alternatives to Agentrq include n8n (Visual workflow automation platform with AI integrations (self-hosted option available)), Zapier (Cloud-based automation tool for connecting apps (less control, easier setup)), LangChain agents (Open-source framework for building custom AI agent workflows in Python), Anthropic's Claude API with custom scripts (Build your own agent system directly using Claude's API). You can also compare Agentrq side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Agentrq? 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/agentrq-agentrq)HTML embed:
<a href="https://agentarmorhq.com/skills/agentrq-agentrq"><img src="https://agentarmorhq.com/api/badge/agentrq-agentrq" alt="AgentArmorHQ Risk Grade for Agentrq" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "agentrq-agentrq"Share with your security lead
Need sign-off to use agentrq? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: agentrq
- **Listing URL:** https://agentarmorhq.com/skills/agentrq-agentrq
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.2k 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:** Requires API key or token
- **Package source:** GitHub (agentrq/agentrq)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/agentrq/agentrq
- **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 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- agentrq
- Source code
- github.com/agentrq/agentrq
- Est. context load
- ~88 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 1.2k GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-22
Community
Discussions for Agentrq
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