# hermes-labs-ai

> Open-source publisher. Listings imported from github.com/hermes-labs-ai — credited to the original author with their license.

- **Listings:** 3
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/hermes-labs-ai
- **Website:** https://github.com/hermes-labs-ai

## Published listings

- [Fidelis](https://agentstack.voostack.com/l/mcp-hermes-labs-ai-fidelis) — MCP server · Free — `agentstack add mcp-hermes-labs-ai-fidelis`
  fidelis is zero-LLM agent memory for Claude Code and AI agents: a local-first memory layer whose default retrieval path uses BM25, dense vectors, and reciprocal rank fusion with no LLM call. It returns your original passages verbatim instead of paraphrasing and runs fully local. Benchmarked on LongMemEval-S. MIT, by Hermes Labs.
- [Hermes Prime](https://agentstack.voostack.com/l/mcp-hermes-labs-ai-hermes-prime) — MCP server · Free · security-reviewed — `agentstack add mcp-hermes-labs-ai-hermes-prime`
  Drift-prevention session-init convention card for fresh Claude Code sessions. Injects a self-contained card so a new session opens with its grounding triggers, calibration rules, and tool-map in scope — instead of re-deriving them at minute 30. Per-project, marker-anchored, idempotent, reversible. Bash installer plus MCP server.
- [Zer0dex](https://agentstack.voostack.com/l/mcp-hermes-labs-ai-zer0dex) — MCP server · Free · security-reviewed — `agentstack add mcp-hermes-labs-ai-zer0dex`
  A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.