Skip to content

Grok & agent systems — May 2026

Strategic snapshot: Grok product posture + Crusty (Hermes) local agent stance + wiki maintenance workflow for https://wiki.darcymenard.com. Cross-links: projects/crusty, Grok-Brief, projects/personal-projects-wiki, projects/openclaw-autonomy-org.

Capability bullets below reflect xAI Grok circa mid-May 2026 (Skills ship, Grok Build beta, tiers). Re-check vendor docs before wiring production automations.

Latest Grok capabilities (mid-May 2026)

  • Skills system (shipped ~May 12–13): reusable, modular workflows and persistent expertise. Invoke via /skill-name or /skill-creator. Supports document generation (docx, pdf, pptx, xlsx), file operations in sandbox, custom automations, and treats Grok as a persistent workspace layer — prebuilt and fully custom skills; integrates with agents.
  • Grok 4.3 + computer use: native ability to write/run code, install dependencies, and produce real output files (documents, presentations, spreadsheets, etc.) inside a sandboxed computer environment. Rolling out to SuperGrok / Premium+ users.
  • Grok Build (early beta, May 14): terminal-based CLI coding agent for professional software engineering — plan/review/approve workflow, parallel sub-agents, integrates with Skills, AGENTS.md, plugins, MCP. Tier-limited (SuperGrok Heavy, ~$300/mo at time of writing). Strong fit for complex codebases and heavy automations.
  • Multi-agent architecture (Grok 4.20 / grok-4.20-multi-agent): multiple specialized agents collaborate in parallel on a shared backbone for deeper research, reasoning, and synthesis. Agent count and effort are configurable.
  • Connectors: native OAuth integrations (Gmail, Google Calendar, Drive, GitHub, Notion, Slack, etc.) for direct read/write inside Grok — scoped and revocable. Caution: prompt-injection risk on sensitive accounts; treat connected inboxes/docs as hostile input surfaces.
  • Tiers: X Premium+ and SuperGrok cover Skills, computer use, and core models solidly for most workflows. SuperGrok Heavy unlocks Grok Build CLI and higher limits / early access.

Crusty + local agent strategy (Hermes + Grok OAuth)

Crusty (dedicated local hardware — see projects/crusty) is the home for persistent agents tuned for always-on work: email/calendar summarization, reminders, content pipelines, publishing gates, etc.

Recommended harness: Hermes Agent (Nous Research — open-source, self-hosted, framed as self-improving) with native xAI Grok OAuth (browser login; uses existing SuperGrok / Premium+ subscription — no separate XAI_API_KEY for covered Grok paths). Hermes supports a Telegram gateway, custom skills/plugins, MCP, memory, and tool use; it can operate on local filesystem, Git, and browser actions where configured.

Why Hermes on Crusty (vs cloud-only Grok)

  • Isolation for sensitive access (e.g. Gmail/Calendar scopes) under your machine and policy boundaries.
  • Always-on without relying on cloud round-trips for routine automation.
  • Self-improving skills loop aligns with iterated local agent ops.
  • Continuity with the existing projects/crusty / projects/openclaw-autonomy-org philosophy (delegated autonomy, Telegram gates, audited execution).

Hybrid model: local Crusty + cloud Grok

Layer Role
Local (Crusty + Hermes) Always-on schedules, Telegram remote control, sensitive-account integrations where posture demands it, routine wiki/repo maintenance intent, sandboxed execution, Git operations after approval.
Cloud (Grok grok.com / subscription Grok) Heavy multi-agent reasoning, deep synthesis, high-quality documents/presentations (Skills + computer use), rapid prototyping — use when frontier tooling or parallel agents beat local economics.

Handoff pattern: use cloud Grok for hard conversations or research; emit structured update payloads (sections, bullets, filenames) for the local agent to apply, diff, gate, commit, push.

Wiki maintenance workflow (wiki.darcymenard.com)

Goal: Keep the public wiki (projects/personal-projects-wiki) a living, agent-maintained knowledge base driven from conversations — browser and mobile Grok, not Crusty.

Active path (2026-06-07): Interim — grok-wiki-maintainer-setup. Use case: talk to Grok about the personal projects wiki → summarize and update the wiki → apply in Cursor. Skill: grok-skills/wiki-maintainer/SKILL.md (/wiki-maintainer).

Blocked: Approach A (fine-grained PAT + Custom MCP api.githubcopilot.com/mcp/) — Grok connector UI is OAuth-only (no Bearer/PAT). Feature request to @xAI for repo-scoped Bearer auth. Do not use built-in GitHub OAuth (whole account).

Architecture (interim — live)

  • Grok (browser / mobile): read https://wiki.darcymenard.com in chat; discuss projects; output wiki update pack (files + deltas + commit message).
  • Cursor (main Mac): apply pack → commit → push → Vercel auto-build.
  • Skill: /wiki-maintainer — propose-only until scoped MCP exists.
  • Crusty / Hermes: unchanged — no wiki git on dedicated machine.

Update flow

  1. /wiki-maintainer — “My personal projects wiki is wiki.darcymenard.com — let’s talk about [project].”
  2. Discuss.
  3. “Summarize what we discussed and update the wiki.”
  4. Grok outputs wiki update pack → Darcy reviews.
  5. Cursor → commit + push → confirm wiki.darcymenard.com.
  6. If What-Im-Working-On.md changed materially → darcymenard.com/projects in personal-website (separate repo).

When Custom MCP supports Bearer (future)

Fine-grained PAT scoped to projects-wiki only → Grok may push after explicit push in-thread. See grok-wiki-maintainer-setup Approach A steps.

Future (deferred — 2026-07-18)

  • GitHub App installed on projects-wiki only + small cloud MCP shim (Fly/Vercel-class) if xAI does not ship PAT auth.
  • Hermes WikiMaintainer on Crusty — optional; not needed for interim.

Security

  • No full-account GitHub OAuth on Grok for wiki.
  • Human gate: review update pack before Cursor push.
  • Public wiki/ only — no secrets in commits.

Canonical cold-start routing for blank Grok threads remains Grok-Brief — this page is architecture/strategy, not the paste-pack.