{
  "schema_version": "1.1",
  "id": "s9:https://github.com/melgarafael/DeskcommCRM",
  "slug": "deskcommcrm-0c300yq",
  "url": "https://feed7.dev/p/deskcommcrm-0c300yq",
  "title": "melgarafael/DeskcommCRM",
  "why_included": "DeskcommCRM is a self-hosted, multi-tenant WhatsApp CRM where AI agents can qualify leads, operate pipelines through MCP, and hand work to humans under audit and budget controls.",
  "summary": "DeskcommCRM combines WhatsApp, a multi-tenant CRM, and agents with **tenant-scoped RAG**, memory, executable skills, audited human handoff, and organization spending caps. The CRM is exposed through **MCP**, while RLS isolation tests gate CI.",
  "practical_implication": "Builders can study it as a concrete agent system: events enter an event_log, a scheduled worker drains them, and agents operate business state under RBAC and audit controls. Installation targets a Docker VPS; updates back up the database, apply a tagged release, and roll back the app image if it breaks.",
  "agent_context": "DeskcommCRM combines WhatsApp, a multi-tenant CRM, and agents with **tenant-scoped RAG**, memory, executable skills, audited human handoff, and organization spending caps. The CRM is exposed through **MCP**, while RLS isolation tests gate CI.\n\nBuilders can study it as a concrete agent system: events enter an event_log, a scheduled worker drains them, and agents operate business state under RBAC and audit controls. Installation targets a Docker VPS; updates back up the database, apply a tagged release, and roll back the app image if it breaks.\n\nThe repository makes broad operational and security claims, but the supplied material does not provide independent validation or workload benchmarks. Deployment still depends on Supabase, a model provider, WhatsApp infrastructure, cron health, and careful handling of production credentials.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/melgarafael/DeskcommCRM",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "tools",
  "domains": [
    "coding",
    "data"
  ],
  "topics": [
    "mcp",
    "skills",
    "agent-memory"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The repository makes broad operational and security claims, but the supplied material does not provide independent validation or workload benchmarks. Deployment still depends on Supabase, a model provider, WhatsApp infrastructure, cron health, and careful handling of production credentials."
  ],
  "connected_context": {
    "meaning": "DeskcommCRM turns several proposed context and orchestration patterns into one vertical, multi-tenant system: business events, scoped retrieval and memory, reusable skills, MCP operations, human handoff, spending limits, RBAC, audits, and CI isolation tests. It supports the value of a shared substrate, but narrows it to tenant boundaries and concrete operations; its broad claims remain unvalidated and its dependency chain adds operational failure points.",
    "corpus_size": 757,
    "generated_at": "2026-09-12T10:05:46.613Z",
    "connections": [
      {
        "title": "The Building Blocks of GTM Orchestration — Arman Vaziri, Ramp",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=VjEP0xqTUI0",
        "feed7_url": "https://feed7.dev/p/the-building-blocks-of-gtm-orchestration-arman-vaziri-ramp-1mjpli3",
        "reason": "DeskcommCRM implements the shared data, durable event processing, skills, and MCP substrate described for GTM orchestration, while adding explicit tenant isolation, spending caps, audit controls, and human handoff."
      },
      {
        "title": "WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=8G_1-3IO4ZQ",
        "feed7_url": "https://feed7.dev/p/wtf-is-the-context-layer-the-missing-infrastructure-for-production-agent-0t47xqf",
        "reason": "Its tenant-scoped RAG and memory are a concrete form of shared business context, but remain embedded in one CRM rather than the portable, versioned context layer proposed across changing agent harnesses."
      },
      {
        "title": "TencentCloud/TencentDB-Agent-Memory",
        "source_name": "GitHub",
        "source_url": "https://github.com/TencentCloud/TencentDB-Agent-Memory",
        "feed7_url": "https://feed7.dev/p/tencentdb-agent-memory-0gx8nnn",
        "reason": "Both govern reusable agent context, but TencentDB treats conversations, skills, docs, and code as a general asset hub, while DeskcommCRM binds memory to tenant-scoped customer operations and RLS enforcement."
      },
      {
        "title": "SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.07449v1",
        "feed7_url": "https://feed7.dev/p/2608-07449v1-1co8km3",
        "reason": "DeskcommCRM’s executable skills create the maintenance problem SkillProx addresses: changes should be evaluated, rolled back on regressions, and pruned when low-value; the repository’s CI isolation tests cover a different but complementary control."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/deskcommcrm-0c300yq",
    "json": "https://feed7.dev/p/deskcommcrm-0c300yq.json",
    "markdown": "https://feed7.dev/p/deskcommcrm-0c300yq.md"
  }
}