Google PageRank for AI agents. 25,000+ tools indexed.

opencode-plusplus MCP Server

whut09/opencode-plusplus

Score: 57.8 Rank #7295 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/whut09--opencode-plusplus)](https://agentrank-ai.com/tool/whut09--opencode-plusplus/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of whut09/opencode-plusplus? Claim this listing →

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++:面向 OpenCode 的 AI 编程可靠性增强框架,为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。

Add AgentRank to Claude Code Discover and compare tools like whut09/opencode-plusplus — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

whut09/opencode-plusplus is a TypeScript tool licensed under MIT. OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++:面向 OpenCode 的 AI 编程可靠性增强框架,为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。 Topics: agent, harness, harness-ai, harness-engineering, loop-engineering, mcp, mcp-tools, mimo-code, mimocode, opencode, opencode-ai, opencode-plugin, code-agent, code-agent-cli, code-agent-harness, code-agents, hallucination-guard, verification, regression-guard.

Ranked #7295 out of 24846 indexed tools.

Ecosystem

TypeScript MIT
agentharnessharness-aiharness-engineeringloop-engineeringmcpmcp-toolsmimo-codemimocodeopencodeopencode-aiopencode-plugincode-agentcode-agent-clicode-agent-harnesscode-agentshallucination-guardverificationregression-guard

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 112

112 stars → growing community

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 4

4 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 11
Description Detailed
License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 63 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for whut09/opencode-plusplus
[![AgentRank](https://agentrank-ai.com/api/v1/badge/whut09--opencode-plusplus)](https://agentrank-ai.com/tool/whut09--opencode-plusplus/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/whut09--opencode-plusplus/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/whut09--opencode-plusplus" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="whut09/opencode-plusplus"></script>

Matched Queries

topic:mcp

From the README

# OpenCode++

[中文说明](README.zh-CN.md)

**A Windows-first Harness plugin for the official OpenCode Desktop application.**

OpenCode++ makes the work around an AI-generated diff visible and reviewable: what it inspected, what it blocked, what it asked to run, and what current evidence actually verified.

## What Problem It Solves

An AI coding session can produce a plausible diff while reading the wrong files, editing outside the intended scope, running an unrelated command, or declaring success without fresh test evidence. OpenCode++ adds a verification control plane around OpenCode Desktop so the model has to work from repository context, explicit edit boundaries, traceable evidence, and a final decision.

OpenCode++ is not another chat application and it is not a replacement model. It is a user-level Desktop plugin that observes the tools OpenCode already exposes and provides Harness tools for:

- selecting relevant files and symbols before blind search;
- preparing task boundaries an
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.