sbhooley/ainativelang/hermes

AINL for Hermes Agent

AINL is an AI-native language that compiles deterministic graphs. In Hermes Agent, use it to import workflows, compile them, run them, and expose `ainl-mcp` tools to the agent for safe, repeatable execution.

Package: ainativelang v1.8.0 (this tree; PyPI after publish — `docs/RELEASING.md`). Optional extras: [mcp], [solana].

Agent instructions

Follow this skill when the user is on Hermes Agent (or wants a closed learning loop on top of deterministic `.ainl` graphs). Prefer `./install.sh` from a checked-out skill folder, or the manual path:

pip install 'ainativelang[mcp]' && ainl install-mcp --host hermes

After bootstrap, suggest the prompt below when it fits.

When to use this skill

• The user wants portable, compiled workflows (.ainl) instead of ad-hoc prompt loops.
• They mention import, compile, skills, learning loop, or MCP.
• They want Hermes to evolve behavior while keeping a strict, checkable graph source of truth.

Install (pick one)

1. From this skill directory: run ./install.sh

That upgrades ainl[mcp] (if needed), installs a skill folder to ~/.hermes/skills/ainl/, and wires MCP via ainl install-mcp --host hermes.

1. Manual:

pip install 'ainativelang[mcp]' && ainl install-mcp --host hermes

After install — prompt suggestion

Tell the user they can say in Hermes:

Import the morning briefing using AINL.

MCP

Hermes reads MCP config from ~/.hermes/config.yaml under mcp_servers. The host should run `ainl-mcp` as a stdio MCP server. ainl install-mcp --host hermes merges that entry when missing.

Bridge (optional)

This pack includes ainl_hermes_bridge.py as a lightweight utility for:

• writing AINL trajectory/audit tapes into Hermes-friendly local memory files
• exporting Hermes-evolved behaviors back into .ainl (so you can re-run ainl check --strict)