Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
It solves the problem of expensive, closed CRM platforms that lock data and charge per feature, especially for businesses selling via WhatsApp. It provides a self-hosted, AI-integrated CRM that can be customized for any niche, with agents that actually operate the CRM (not just chatbots), and gives full data ownership and privacy (LGPD).
Deployment reality
The available setup signal starts with: curl -fsSL https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/hostgator-setup-kit/comecar.sh | bash. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build a complete AI-driven sales operation for any business that sells via chat, including e-commerce, clinics, real estate, agencies, and service providers. The AI agents can attend, qualify, move leads, trigger automations, and hand off to humans, with RAG per tenant and self-improvement from resolved conversations. The MCP server exposes the entire CRM to external agents, enabling deep integrations and automation. The ceiling is a fully autonomous sales pipeline that learns and improves over time, with human oversight where needed.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
melgarafael/DeskcommCRM is tracked as a TypeScript project in the AI Agent, MCP Server, LLM Tool, AI App, Automation area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 378 total stars, with +28 today, +0 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Active; the latest push was 17 days ago, and the open issue queue is 8, about 2.12% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 194 forks and 378 watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need AI prototypes, LLM workflows, and agent-style applications. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 29. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyMIT is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
378 Stars
Reuse
194 Forks
Attention
378 Watchers
Maintenance
active
License
MIT
Open issues
8
DeskcommCRM is an open-source, self-hosted CRM and sales operating system with AI agents that handle, qualify, and sell on WhatsApp. It offers multi-tenant support, LGPD compliance, and a one-command installation for production, positioning itself as an alternative to proprietary CRMs like Kommo, Octadesk, and Intercom.
Key Features
- AI agents with tenant-scoped RAG, sentiment analysis, audited human handoff, and budget control. - WhatsApp-native via WAHA with multi-number support, anti-ban throttling, and STOP detection. - Multi-tenant with row-level security and LGPD-by-design, plus webhooks and automation for lead capture and workflow.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
MCP Server
Model Context Protocol servers, clients, and integrations
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
AI App
End-user AI applications and AI-native product examples
Automation
Workflow automation, integration glue, and orchestration
curl -fsSL https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/hostgator-setup-kit/comecar.sh | bash65
Health Score
Active
Commit Activity
Apr 28, 2026
Created
Aug 6, 2026
Last push
+29
Today's growth
+29
7-day growth
+29
30-day growth
Forks
Open
Watchers
melgarafael
GitHub profileopenclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
✓
License
✓
Forked
✓ Active
Maintained
Problem Solved
It solves the problem of expensive, closed CRM platforms that lock data and charge per feature, especially for businesses selling via WhatsApp. It provides a self-hosted, AI-integrated CRM that can be customized for any niche, with agents that actually operate the CRM (not just chatbots), and gives full data ownership and privacy (LGPD).
Capabilities
Developers can build a complete AI-driven sales operation for any business that sells via chat, including e-commerce, clinics, real estate, agencies, and service providers. The AI agents can attend, qualify, move leads, trigger automations, and hand off to humans, with RAG per tenant and self-improvement from resolved conversations. The MCP server exposes the entire CRM to external agents, enabling deep integrations and automation. The ceiling is a fully autonomous sales pipeline that learns and improves over time, with human oversight where needed.
Bottom Line
DeskcommCRM is ideal for businesses and developers who want a customizable, self-hosted CRM with integrated AI agents for WhatsApp sales, and who value data ownership and cost savings. It is not suitable for those who prefer a fully managed, no-maintenance solution or lack technical resources. The key trade-off is between control and flexibility versus the burden of self-hosting and the maturity of the AI features.