Models & MCPPlugin

agentrq

agentrq/agentrq

agentrq is a tool for DeepSeek Harness. 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.

View repository Project homepage

Stars: 1.1k
Forks: 79
Issues: 16
Update: 38 days

REVIEW SCORECARD

Review Scorecard

8.3/10Good

License compliance9.0

Engineering quality8.7

Content completeness8.0

Repository scale7.0

Maintenance activity8.0

✓ No risk detected · Automated scan results are for reference only, not an official endorsement

AI DEEP REVIEW

Worth AI Review

7.0/10Consider

A promising self-hosted human-in-the-loop task manager for AI agents, but installation details are missing from the prov

Code quality7

README describes a decoupled Go/Fiber backend with GORM/SQLite and an mcp-go SSE server, but no tests, CI, or install/dev instructions are visible to confirm engineering rigor.

Security6

No install command or download mechanism is shown, and the README emphasizes self-hosting and on-device browser models, but no security posture can be verified from the given excerpt.

Utility8

It addresses a real pain point by giving agents an MCP-visible task board with scheduling, events, workflows, and human approval, which is a common need for agentic workflows.

Maintenance8

Last updated 2026-08-26 with 1090 stars and an active Discord community, indicating ongoing maintenance rather than an abandoned project.

Documentation6

The README explains features and architecture in depth with GIFs, but the install command is unknown and no setup or usage instructions are provided in the excerpt.

Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.

PROJECT READMEREADMEExpandCollapse

Loading GitHub README...

PROJECT TOPICS

Project topics

acp-client acp-gateway agentic-ai agentic-workflow agents claude-code deepseek-harness deepseek-harness-plugin dsh-plugin hermes-agent mcp mcp-server openclaw opencode supervisor task task-manager task-scheduler todo

VALIDATION LADDER

Validation progress

Structure check pending

01Store discoveryPassed

02ClassificationPassed

03Structure checkPending

04Sandbox validationPending

FAQ

Frequently Asked Questions

What is agentrq used for?

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 an

How popular is agentrq?

agentrq has 1,090 stars and 79 forks on GitHub, last updated 2026-08-26.

What license does agentrq use?

agentrq is distributed under the Apache-2.0 license.

Is agentrq compatible with DeepSeek Harness?

agentrq is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE

Classification evidence

Project typePlugin

Feature categoryModels & MCP

Rule confidenceHigh

The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agentic-workflow、claude-code、mcp、mcp-server、task-scheduler。

agentrq

Review Scorecard

Worth AI Review

Project topics

Validation progress

Frequently Asked Questions

Classification evidence

Related projects

dsh-purge

AI-Novel-Writer

sandbase-harness

dsh-desktop

memtrace-public

MisakaNet