loglyBusiness & marketing
mureo
Local-first AI ad ops control plane supporting Google Ads, Meta Ads, and cross-platform analysis.
- Operations
- Data analysis
- Automation
- CLI
- Windows
- macOS
- Linux
- Self-hostable
- Runs locally
- Docker supported
- Popularity
- 43 Stars
- GitHub stars
- Recent activity
- 9/2/2026
- Updated in the last 30 days
- License
- APACHE-2.0
- Permissive
Why it matters
We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.
Problem
Integrating AI agents into ad operations often leads to credential leak risks, fragmented cross-platform APIs, and a lack of strategic guardrails or audit trails for execution safety.
Practical value
Provides a local web interface and CLI with synthetic demo modes, read-only data import for risk-free auditing, strategy-file alignment, and append-only action logs with rollback options.
Innovation / differentiation
Implements a local-first control plane bridging general AI agents with ad platform MCPs, enforcing business context via local strategy files and safety guardrails.
Leverage potential
Leverages existing AI agent terminals and MCP protocols while offering spreadsheet imports to bypass lengthy OAuth app review processes.
Why now
Arrives as Model Context Protocol (MCP) and terminal AI agents gain momentum, filling the gap for domain-specific safety controls in advertising operations.
Community activity
In the last 90 days there were 179 new issues and 386 pull requests; the bounded issue/PR samples include 3 issue authors and 1 PR contributors, with at least 50 releases.
Maintainer responsiveness
The 100-issue window sample had a 99% close rate, and the 100-pull-request sample had a 100% merge rate. Maintainer-response observations covered 100% of that issue sample, with a 18% response rate and median first response of 3.9 hours.
Key highlights
- Strategy-grounded decisions reading local STRATEGY.md files for accurate business context
- Read-only BYOD mode for instant XLSX report exports without requiring OAuth credentials
- Local-first privacy architecture ensuring credentials and API tokens never leave your system
Quick start
How it is installed, how hard it is, and where to start.
Where it runs
To be confirmed
Difficulty
To be confirmed
- 01Install the mureo CLI package using pip.
- 02Launch the local configuration dashboard bound to localhost.
- 03Initialize a local demo scenario to test mureo on synthetic account data.
- 04Run the daily check command inside your AI agent interface.
- 05Import local XLSX ad performance exports for read-only analysis.
- 06Run the onboarding interview command to build your STRATEGY.md file.
Best for
- Teams that want data on their own servers
- Developers who want to try it on their machine
- People who prefer Docker deploys
More about it
mureo provides an open-source, local-first control plane for AI-driven ad operations. Designed to work alongside developer AI tools like Claude Code, Cursor, Codex, and Gemini, mureo bridges official advertising platform MCPs to give agents clear strategic boundaries and audit logs. Users can get started without complex OAuth approvals using BYOD mode by importing XLSX data exports from platforms like Google Ads and Meta Ads. For teams needing live execution, mureo supports full API integrations to automatically rebalance budgets, refresh creatives, and clean up unhelpful search terms under safety guardrails.
Sources
Each field shows its status and source — expand to review.
15 · Expand
Sources
Each field shows its status and source — expand to review.
capability tags
Verifieddata_analysis, automation
Source: admin_cms · cms editor · 8/30/2026
editor note
Verified{"en":"mureo sets itself apart by bringing local-first execution and strategy constraints to AI ad operations. By operating over platform MCPs or offline Excel exports (BYOD), it allows teams to audit campaign waste, evaluate search terms, and test recommendations without sending credentials to third-party cloud services.","zh":"mureo 最大的特点是将 AI 智能体（如 Claude Code 或 Cursor）接入广告平台 MCP，并严格保证数据与凭据留在本地。它支持直接导入 Excel 报表进行只读分析（BYOD 模式），也能通过 OAuth 联动真实 API 自动执行广告调整，配合 STRATEGY.md 策略文件可规避纯数据工具常见的逻辑误判。"}
Source: admin_cms · cms editor · 8/30/2026
how to use
Verified{"steps":[{"en":"Install the mureo CLI package using pip.","zh":"使用 Python 包管理器安装 mureo 核心工具包。"},{"en":"Launch the local configuration dashboard bound to localhost.","zh":"启动本地配置界面以绑定所选的 AI 客户端（如 Claude Code）。"},{"en":"Initialize a local demo scenario to test mureo on synthetic account data.","zh":"初始化演示场景体验不含真实账户凭据的策略分析流程。"},{"en":"Run the daily check command inside your AI agent interface.","zh":"在 AI 智能体终端中运行日常检查指令查看分析报告。"},{"en":"Import local XLSX ad performance exports for read-only analysis.","zh":"导入本地导出的 XLSX 广告数据报表（BYOD 只读模式）。"},{"en":"Run the onboarding interview command to build your STRATEGY.md file.","zh":"执行初始化问卷以生成项目策略文件 STRATEGY.md。"}],"installAt":"unknown","difficulty":"unknown"}
Source: admin_cms · cms editor · 8/30/2026
intro
Verified{"en":"mureo provides an open-source, local-first control plane for AI-driven ad operations. Designed to work alongside developer AI tools like Claude Code, Cursor, Codex, and Gemini, mureo bridges official advertising platform MCPs to give agents clear strategic boundaries and audit logs. Users can get started without complex OAuth approvals using BYOD mode by importing XLSX data exports from platforms like Google Ads and Meta Ads. For teams needing live execution, mureo supports full API integrations to automatically rebalance budgets, refresh creatives, and clean up unhelpful search terms under safety guardrails.","zh":"mureo 是一款开源且本地优先的 AI 广告运营控制台，能帮助市场团队与开发者通过 AI Agent（包括 Claude Code、Cursor、Codex 与 Gemini）管理多平台广告账户。它依托官方广告平台 MCP，构建了一套包含策略约束、安全拦截和操作审计的代理运行机制。 在使用过程中，mureo 支持无需 OAuth 接入的 BYOD 模式，用户只需从 Google Ads 或 Meta Ads 导出 XLSX 报表即可生成全盘诊断报告；同时，它也提供基于 OAuth 的 Live API 模式，可在确认策略后执行预算重平衡与搜索词清理等实际写操作。"}
Source: admin_cms · cms editor · 8/30/2026
Latest release
Verifiedv0.17.3
Source: GitHub API · latest_release=v0.17.3 · 9/5/2026
License
VerifiedApache-2.0
Source: GitHub API · license.spdx_id=Apache-2.0 · 9/5/2026
needs api key
VerifiedNo
Source: admin_cms · cms editor · 8/30/2026
One-liner
Verified{"en":"Local-first AI ad ops control plane supporting Google Ads, Meta Ads, and cross-platform analysis.","zh":"面向广告运营的本地优先 AI Agent 协作框架，支持 Google Ads 与 Meta Ads 等多平台分析。"}
Source: admin_cms · cms editor · 8/30/2026
Platforms
Verifiedwindows, macos, linux
Source: admin_cms · cms editor · 8/30/2026
Category hint
Inferred from materialsai-apps
Source: Project README · hint=ai-apps · 8/22/2026
product forms
Verifiedcli
Source: admin_cms · cms editor · 8/30/2026
role tags
Verifiedoperations
Source: admin_cms · cms editor · 8/30/2026
supports docker
VerifiedYes
Source: Repository file · dockerfile=true; compose=false · 9/5/2026
supports local
VerifiedYes
Source: admin_cms · cms editor · 8/30/2026
supports self host
VerifiedYes
Source: admin_cms · cms editor · 8/30/2026
Related projects
Other verified projects matched by category, capabilities, and intended roles.
RustySEO
Free, cross-platform SEO toolkit for website crawling, log analysis, and optimization.
prometheus
A monitoring system that scrapes target metrics, queries them with PromQL, evaluates rules, and triggers alerts when configured conditions are met.
ragflow
An open-source RAG engine fusing deep document understanding and agent capabilities to build grounded context layers for LLMs.
needle
A small local-model Python package for tool calling and structured extraction, with offline inference, confidence thresholds, LoRA fine-tuning, and model export.
steampipe
A zero-ETL tool to query APIs and cloud services directly using SQL without data replication.
clearml
A machine-learning development and MLOps platform for experiment tracking, remote orchestration, data versioning, and model workflows with hosted or self-hosted servers.