Search results

1321 results for “skills”

  1. CortexlayerPlugins · Skills, plugins & MCPCortexLayer memory provider — page-linked long-term memory with link-expansion retrieval, wired into Hermes' automatic per-turn recall (prefetch) and persistence (sync_turn), plus a pre-compress checkpoint so evidence…
  2. Usage FlamePlugins · Skills, plugins & MCPPinned glowing chip + fire-themed panel with live subscription-quota windows (remaining %, reset countdown, burn-rate pace and run-out forecast with sparkline history) for every provider Hermes reports usage for.
  3. Hermes Self-Healing ContextPlugins · Skills, plugins & MCPIntercepts runtime errors and dynamically patches the context window using local SQLite FTS5 memory for zero-downtime recovery.
  4. Yolo AutoPlugins · Skills, plugins & MCPYolo-Auto: flat-rate OpenAI-compatible API with plan-filtered live model discovery.
  5. Intelligent MemoryPlugins · Skills, plugins & MCPLocal-first Arabic/English intelligent memory with canonical facts, conflict lifecycle, bounded recall, and selective Hermes cloud enrichment.
  6. Ai Usage TrackerPlugins · Skills, plugins & MCPLive subscription-quota windows for every AI provider Hermes can route to, as a desktop page plus a status-bar chip, with a per-profile picker — Codex, Claude, Copilot, OpenCode Go/Zen, Z.AI, Kimi, MiniMax, Nous…
  7. Gbrain Retrieval ReflexPlugins · Skills, plugins & MCPpre_llm_call hook plugin, enabled with hermes plugins enable: injects ambient context from a GBrain instance before each turn (volunteer_context, then a hybrid-query fallback).
  8. Next StepsPlugins · Skills, plugins & MCPNext-step suggestions under the Hermes Desktop composer after each turn: local Ollama inference, per-session state, target routing (session, new tab, bots, kanban), tiny-model capacity profiles, EN/DE UI.
  9. Lightningai Rate LimitPlugins · Skills, plugins & MCPPer-process throttle for Lightning AI (https://lightning.ai/api/v1) keeping LLM requests within the ~15 requests/min limit, using an in-memory token bucket.
  10. Excel LinePlugins · Skills, plugins & MCPExcel-backed hierarchical long-term memory tree (10-row cap per workbook, dynamic branching, leaf pointers).
  11. Jev Memory SelectorPlugins · Skills, plugins & MCPAgent Plugins v1 package: one skill plus one stdio MCP server (memory_select) started with uv run from the checkout.
  12. MemobasePlugins · Skills, plugins & MCPMemobase memory provider — self-hosted user profile + event timeline recall, with hybrid BM25/vector/entity retrieval and automatic per-turn prefetch.
  13. MetronixPlugins · Skills, plugins & MCPMetronix memory provider for Hermes with prefetch recall and built-in memory write-through.
  14. Yantrikdb Hermes DashboardPlugins · Skills, plugins & MCPLocal-only YantrikDB dashboard for Hermes Agent memory operations
  15. Profile PanePlugins · Skills, plugins & MCPDisclosure — copies .env key values (and opt-in auth.json backups) between profiles; rewrites other profiles' SOUL, memory and config.yaml.
  16. Advanced DelegationPlugins · Skills, plugins & MCPTwo extra delegation modes for delegate_task, next to the built-in default.
  17. Mcp ServePlugins · Skills, plugins & MCPRun Hermes as an MCP server: hermes mcp-serve lets any MCP client (Claude Code, Claude Desktop, Cursor, Codex) list and read your messaging conversations, poll live events, send messages and answer approvals over stdio.
  18. Hermes Telegram BusinessPlugins · Skills, plugins & MCPObserve-with-approval Telegram Business Mode (secretary bot): Hermes drafts replies to your customers' messages and DMs each draft to you with Send, Edit and Discard buttons; nothing reaches a customer until you tap…
  19. Agent ImportersPlugins · Skills, plugins & MCPhermes import-agent: import an OpenClaw (~/.openclaw, or legacy ~/.clawdbot / ~/.moltbot), Claude Code (~/.claude), Codex CLI (~/.codex) or Cursor (~/.cursor) setup into Hermes in one command.
  20. Agent BlackboxPlugins · Skills, plugins & MCPSecurity for agents: checks every tool call and model request before it runs against a curated, verifiable threat graph (prompt injection, dangerous commands, malicious packages, unsafe skills, phishing and drainer…