{"data":{"slug":"sbhooley-ainativelang","name":"ainativelang","tagline":"A compact, graph-canonical AI-native programming system","github_url":"https://github.com/sbhooley/ainativelang","owner":"sbhooley","repo":"ainativelang","owner_avatar_url":"https://avatars.githubusercontent.com/u/6730846?v=4","primary_language":"Python","stars":652,"forks":22,"topics":["agent-orchestration","ai-agents","ai-native-language","ainl","claude-code","compiler","deterministic-execution","domain-specific-language","dsl","graph-ir","langchain-alternative","llm-orchestration","mcp","model-context-protocol","multi-agent","openai","openclaw","prompt-engineering","python","workflow-engine"],"archived":false,"github_pushed_at":"2026-09-03T15:50:51+00:00","maintenance_label":"Active","stars_delta_30d":-116,"url":"https://www.graphcanon.com/tools/sbhooley-ainativelang","markdown_url":"https://www.graphcanon.com/tools/sbhooley-ainativelang.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sbhooley-ainativelang","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sbhooley-ainativelang","description":"AINL helps turn AI from \"a smart conversation\" into \"a structured worker.\"  It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops.  AINL is a compact, graph-canonical, AI-native programming system for (READ: README)","homepage_url":"https://ainativelang.com","license":"Apache-2.0","open_issues":12,"watchers":11,"ai_summary":"AINL is designed for teams building structured and repeatable AI workflows with multiple steps, state management, tool use, and lower reliance on long prompt loops.","readme_excerpt":"## For agents — install AINL (one step)\n\nIf you are an AI coding agent (Claude Code, Cursor, Cline, Codex, Aider, …)\nor any MCP-capable runtime and the user wants AINL added to their stack,\nrun **one command**:\n\n```bash\npipx install 'ainativelang[mcp]' && ainl setup --auto\n```\n\nFallback if `pipx` is unavailable:\n\n```bash\npython3 -m pip install --user 'ainativelang[mcp]' && ainl setup --auto\n```\n\nThat is the entire install. The `setup` command auto-detects every host\npresent (Claude Code project + user, Cursor, Cline, Codex CLI/Desktop,\nClaude Desktop, OpenClaw, Hermes, ArmaraOS, or any generic MCP host),\nmerges the right MCP server entry into each config file (atomic write,\ntimestamped backup), and verifies with `ainl doctor`. Idempotent — safe\nto re-run.\n\nIf a host is not auto-detected, run `ainl setup --print-config` for a\npaste-ready stdio MCP server block.\n\nMachine-readable spec: [`.agent-install.json`](./.agent-install.json) ·\nDesign: [`docs/architecture/2026-05-05-agent-install-simplification.md`](docs/architecture/2026-05-05-agent-install-simplification.md).\n\n---\n\n---\n\n# 1. Install the CLI\npip install ainativelang\n\n---\n\n# Install with dev + web extras\npython -m pip install --upgrade pip\npython -m pip install -e \".[dev,web]\"\n\n---\n\n### Getting started with includes\n\nPull in shared subgraphs from `modules/` (paths resolve next to your source file, then CWD, then `./modules/`):\n\n```ainl\ninclude \"modules/common/retry.ainl\" as retry\n\nL1: Call retry/ENTRY ->out J out\n```\n\nSee **Includes & modules** below for `timeout.ainl`, strict rules, and the starter table.\n\n**AI agents:** See `docs/agents/openclaw-quickstart.md` for a full agent onboarding guide, or `docs/BOT_ONBOARDING.md` for the machine-readable bootstrap path.\n\n**Deeper setup:** See `docs/INSTALL.md` for platform-specific install, Docker, and pre-commit setup.\n\n---\n\n---\n\n### Install AINL as a ZeroClaw skill\n\n```bash\nzeroclaw skills install https://github.com/sbhooley/ainativelang/tree/main/skills/ainl\n```\n\nThis installs the AINL importer, runtime shim, and MCP tools directly into ZeroClaw.\n\n**Bootstrap** (PyPI self-upgrade, **`ainl-mcp`** in **`~/.zeroclaw/mcp.json`**, **`~/.zeroclaw/bin/ainl-run`**, **`PATH`** hint): from the skill directory run **`./install.sh`**, or run **`ainl install-mcp --host zeroclaw`** (use **`--dry-run`** / **`--verbose`** as needed). Alternative skill URL (standalone repo, when published): `https://github.com/sbhooley/ainl-zeroclaw-skill`.\n\n**Try in chat:** *“Import the morning briefing using AINL.”* (Then point the agent at a Clawflows URL, a preset from **`ainl_list_ecosystem`**, or **`ainl import markdown …`**.)\n\nDetails: **[`docs/ZEROCLAW_INTEGRATION.md`](docs/ZEROCLAW_INTEGRATION.md)** · skill files: **[`skills/ainl/README.md`](skills/ainl/README.md)**.\n\n---\n\n### Install AINL as an OpenClaw skill\n\n[OpenClaw](https://openclaw.ai/) uses **npm** + **`openclaw onboard`** for the host CLI. AINL is added as a **skill folder** (not via **`zeroclaw skills install`**): copy **[`skills/openclaw/`](skills/openclaw/)** to **`~/.openclaw/skills/`** or **`<workspace>/skills/`**, or install from **ClawHub** when the skill is listed there.\n\n**Bootstrap** (PyPI self-upgrade, **`mcp.servers.ainl`** in **`~/.openclaw/openclaw.json`**, **`~/.openclaw/bin/ainl-run`**, **`PATH`** hint): from the skill directory run **`./install.sh`**, or run **`ainl install-mcp --host openclaw`** (use **`--dry-run`** / **`--verbose`** as needed). **`install.sh`** may run **`npm install -g openclaw@latest`** when npm is on PATH; set **`OPENCLAW_SKIP_NPM=1`** to skip.\n\nOnce bootstrapped, the OpenClaw bridge automatically activates AINL's intelligence layer, including the cap auto-tuner and memory hydration/embedding pilot. This creates a self-managing runtime that continuously adjusts execution caps and prunes caches based on observed token usage — helping sustain **90–95%** token savings on high-frequency monitors and digests with zero recurring LLM orchestration cost (see **","github_created_at":"2026-03-10T05:25:54+00:00","created_at":"2026-07-11T11:54:04.26415+00:00","updated_at":"2026-09-20T06:44:11.830078+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agent-orchestration","name":"agent-orchestration"},{"slug":"ai-native-language","name":"ai-native-language"},{"slug":"deterministic-execution","name":"deterministic-execution"},{"slug":"domain-specific-language","name":"domain-specific-language"},{"slug":"graph-ir","name":"graph-ir"},{"slug":"langchain-alternative","name":"langchain-alternative"},{"slug":"llm-orchestration","name":"llm-orchestration"},{"slug":"model-context-protocol","name":"model-context-protocol"}],"trust":{"provenance":{"is_fork":false,"github_id":1177523998,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:44:09.151Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":16,"last_release_at":"2026-04-27T15:54:22Z","stars_delta_30d":-116,"open_issues_delta_30d":0},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:54:05.400Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:44:10.398Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T06:44:10.398Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T06:44:10.398Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:44:10.398Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use with the option of paid support or services not detailed here."},"requirements":null,"constraints":{"pricing_model":"freemium"},"when_to_use":["When building structured and repeatable AI workflows that require multiple steps and well-defined state management.","For teams needing tools where execution does not heavily rely on long prompt loops, facilitating more deterministic behavior.","If your project requires a compact graph-canonical approach for orchestration of AI-native programming tasks."],"when_not_to_use":["When the primary workflow involves frequent modifications with minimal planning or less structured iterations as AINL focuses on repeatable and predictable execution paths.","For projects where long prompt loops are essential to capture complex workflows, due to AINL's lower reliance design on them."],"source":"enrich:decision_facts","observed_at":"2026-07-12T08:53:17.273Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use with the option of paid support or services not detailed here."},{"label":"Adopt for","value":"Decision-critical facts about 'ainativelang' are extracted below."},{"label":"License detail","value":"AINL is available under the Apache-2.0 license, which allows for free use in both open source and commercial projects with attribution."}]}}