Hermes Prime
Verified · 23 days agoRead-only stdio MCP server for a versioned convention card in Claude Code.
Read-only stdio MCP server for a versioned convention card in Claude Code.
Parametric CAD as code: model 3D-printable parts on an exact B-rep kernel, measured.
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
Local-first governed MCP memory backend for coding agents.
Shared memory for coding agents: projects, reusable code, sessions and commits across machines
Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.
Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
Pre-execution cost estimation for LLM agent workflows with calibration learning
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
LLM-operable Midjourney pipeline: 21 MCP tools to compose, generate, curate with vision, and log.
Agent-native parametric 3D CAD: model machines, validate them and emit shop drawings
MCP for Yandex Direct: manage ad campaigns & analytics from Claude or ChatGPT
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
Verified KiCad footprints, symbols & 3D models for AI agents. No signup, CC-BY-4.0, quality-gated.
Create, read and live-edit visual boards, Kanban plans, Gantt timelines and diagrams with AI agents.
Autonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.
Self-hosted remote MCP memory server for ChatGPT and AI agents.
Human visual review for agent-built HTML: publish artifacts, pull anchored comments, push fixes.
Ad network for AI agents — monetize MCP servers with contextual ads. 70% revenue share.
OPC UA companion spec types, namespace dependencies, and engineering units for AI agents