# ainativelang

> 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, v

- **URL**: https://www.freshcrate.ai/projects/ainativelang
- **Author**: sbhooley
- **Category**: MCP Servers
- **Latest version**: `v1.8.0` (2026-04-27)
- **License**: Apache-2.0
- **Source**: https://github.com/sbhooley/ainativelang
- **Homepage**: https://ainativelang.com
- **Language**: Python
- **GitHub**: 72 stars, 2 forks
- **Registry**: github
- **Tags**: `agent-orchestration`, `ai-agents`, `ai-native-language`, `ainl`, `claude-code`, `compiler`, `deterministic-execution`, `domain-specific-language`, `prompt-engineering`, `python`

## 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)

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.8.0` | 2026-04-27 | High | PyPI: **`ainativelang` 1.8.0** — `pip install -U 'ainativelang[mcp]'`  ### Highlights - **MCP authoring:** `ainl_get_started` with `wizard_state_json`; `ainl_step_examples`; resource `ainl://strict-valid-families`; `ainl_validate` / `ainl_compile` include `contract_validation_status` and `contract_alignment` (`mismatched_calls` vs `ADAPTER_CONTRACTS`). Hub: [MCP_AINL_WIZARD_AND_CORPUS.md](https://github.com/sbhooley/ainativelang/blob/main/docs/operations/MCP_AINL_WIZARD_AND_CORPUS.md). - **HTTP |
| `v1.4.6` | 2026-04-09 | High | ## AINL v1.4.6 — Samples + OpenSpace harness (2026-04-11)  **PyPI / runtime:** **ainativelang 1.4.6** — **RUNTIME_VERSION 1.4.6**.  - **Samples:** `apollo-x-bot/api-cost-monitor.ainl`, `demo/test_openspace_http.ainl`, and root `run_openspace_test.py` (portable paths) for OpenSpace / promoter experiments. - Full details: [docs/CHANGELOG.md](https://github.com/sbhooley/ainativelang/blob/v1.4.6/docs/CHANGELOG.md) (§ v1.4.6).  Install: `pip install -U "ainativelang[mcp]>=1.4.6"` |
| `v1.4.4` | 2026-04-08 | High | ## ainativelang 1.4.4  PyPI packaging release; version surfaces aligned. See `docs/CHANGELOG.md` and `docs/RELEASE_NOTES.md`.  - **emit_solana_client** discoverability header uses **RUNTIME_VERSION** - **Core builtins** (v1.4.3 line): comparisons, trim/strip, startswith/endswith, keys/values, coercions - **MCP**: `frame_hints`, workspace limits file, auto-cache, docs |
| `v1.4.2` | 2026-04-08 | Medium | ## AINL 1.4.2 (2026-04-07)  Intelligence host adapter policy (`AINL_ALLOW_IR_DECLARED_ADAPTERS`), MCP/runner grant alignment, compiler strict-mode fixes for label jumps, expanded adapter tooling/manifest, intelligence graph fixes, `demo/.ainl-library-skip` for App Store filtering.  **Full notes:** [CHANGELOG.md](https://github.com/sbhooley/ainativelang/blob/v1.4.2/docs/CHANGELOG.md#v142-april-7-2026--intelligence-path-policy-mcprunner-alignment-compiler-strict-mode--tooling) |
| `v1.4.1` | 2026-04-03 | Medium | Release 1.4.1 — offline LLM provider, wishlist examples, fanout, file-backed cache, core.GET, serve/LLM wiring, docs. See docs/CHANGELOG.md. |
| `v1.4.0` | 2026-04-01 | Medium | **Full Changelog**: https://github.com/sbhooley/ainativelang/compare/v1.3.4...v1.4.0 |

## Citation

- HTML: https://www.freshcrate.ai/projects/ainativelang
- Markdown: https://www.freshcrate.ai/projects/ainativelang.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/ainativelang/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._