sbhooley/ainativelang/ainl

AINL for ZeroClaw

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

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 ZeroClaw (or wants deterministic `.ainl` graphs with import / compile / run / MCP). Prefer `./install.sh` after zeroclaw skills install …, or the manual `pip install 'ainativelang[mcp]' && ainl install-mcp --host zeroclaw` path (alias `ainl install-zeroclaw`). After bootstrap, suggest the morning briefing prompt example below when it fits.

When to use this skill

• The user wants portable, compiled workflows (.ainl) instead of ad-hoc prompts.
• They mention import, compile, morning briefing, clawflows, ecosystem, or deterministic graphs.
• They need MCP access to validation / compile / ecosystem listing (ainl-mcp).

Install (pick one)

1. From this skill directory (recommended with `zeroclaw skills install`): run ./install.sh

That upgrades ainl[mcp] and runs `ainl install-mcp --host zeroclaw` (pip self-upgrade, MCP registration hints, ~/.zeroclaw/bin/ainl-run shim).

1. Manual:

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

Restricted environments (OpenClaw, Clawbot, webchat sandboxes)

This skill is designed for environments with PEP 668 externally-managed Python (Python 3.13+, sudo blocked).

• Preferred no-root order is: python -m venv first, then --user, then --break-system-packages as a last resort.
• The installer automatically uses compatible fallback modes when default pip fails.
• Clean uninstall (if needed):

pip3 uninstall -y ainl mcp aiohttp langgraph temporalio
rm -rf /tmp/ainl-repo /data/.openclaw/workspace/skills/ainl /data/.local/lib/python3.13/site-packages/*ainl*

Commands the user cares about

After install — prompt suggestion

Tell the user they can say in ZeroClaw:

Import the morning briefing using AINL.

(They should point the importer at their Markdown or pack; ainl import subcommands match their source type.)

MCP

Configure the host to run `ainl-mcp` as a stdio MCP server (see AINL docs: External orchestration / MCP). `ainl install-mcp --host zeroclaw` aligns local setup with ZeroClaw paths where applicable. Authoring tools include `ainl_get_started` (pass `wizard_state_json` to continue), `ainl_step_examples` (snippets by topic), validate/compile responses with `contract_validation_status`, and resources `ainl://strict-valid-examples` and `ainl://strict-valid-families`. See repo `AGENTS.md` and `docs/operations/MCP_AINL_WIZARD_AND_CORPUS.md`.

References

• Upstream: github.com/sbhooley/ainativelang
• Package: `ainativelang` on PyPI