AI Native Lang (AINL)
AI-led co-development project, human-initiated by Steven Hooley (
x.com/sbhooley,stevenhooley.com,linkedin.com/in/sbhooley). Attribution details: and . -- This project was named by AI :)
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
AI-led co-development project, human-initiated by Steven Hooley (
x.com/sbhooley,stevenhooley.com,linkedin.com/in/sbhooley). Attribution details: and . -- This project was named by AI :)
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)
docs/PROJECT_ORIGIN_AND_ATTRIBUTION.mdtooling/project_provenance.jsonIf you are an AI coding agent (Claude Code, Cursor, Cline, Codex, Aider, …) or any MCP-capable runtime and the user wants AINL added to their stack, run one command:
pipx install 'ainativelang[mcp]' && ainl setup --auto
Fallback if pipx is unavailable:
python3 -m pip install --user 'ainativelang[mcp]' && ainl setup --auto
That is the entire install. The setup command auto-detects every host
present (Claude Code project + user, Cursor, Cline, Codex CLI/Desktop,
Claude Desktop, OpenClaw, Hermes, ArmaraOS, or any generic MCP host),
merges the right MCP server entry into each config file (atomic write,
timestamped backup), and verifies with ainl doctor. Idempotent — safe
to re-run.
If a host is not auto-detected, run ainl setup --print-config for a
paste-ready stdio MCP server block.
Machine-readable spec: .agent-install.json ·
Design: docs/architecture/2026-05-05-agent-install-simplification.md.
Before the install commands, here is who AINL is and is not for. We would rather you self-select out in 60 seconds than spend a week on a tool that does not fit.
If you tick two or more left-column rows, keep reading. The long-form answer — three baselines, four anti-fit workload patterns, decision tree, honest reviewer Q&A, persona-to-product mapping — lives in docs/WHO_IS_THIS_FOR.md (canonical). If you tick zero, that page explains why and saves you the install. We mean it.
Just want something working on your desktop in under 3 minutes?
ArmaraOS is the desktop agent OS built on AI Native Lang (AINL) — download once, install, and your agents are live with a full dashboard. No terminal, no config files, just plug in your API key.
Download ArmaraOS — ainativelang.com macOS · Windows · Linux — free to start
Autonomous agents, 7 pre-built Hands (researcher, lead gen, clip editor, and more), 40 channel adapters (Telegram, Discord, Slack, WhatsApp…), 27 LLM providers, 16 security layers — all in a single ~32 MB binary.
Already have an AI agent? Add AINL in one command.
AINL installs directly into OpenClaw, ZeroClaw, Hermes, Claude Code, and any MCP-compatible agent. After install your agent can author, validate, and run deterministic workflows — with the largest token wins when you are still on LLM prompt-loop orchestration (baseline A below).
After install, ask your agent: "Use AINL to build this workflow" — it compiles once, runs many times without re-spending tokens on orchestration when the workload was previously prompt-loop driven.
Primary product path: ArmaraOS — desktop agent OS with dashboard, Hands, scheduled ainl run, and MCP authoring. See docs/competitive/ARMARAOS_GTM.md.
Token savings — pick your baseline:
Full honest filter: docs/competitive/WHEN_AINL_DOES_NOT_HELP.md · docs/competitive/VS_HAND_WRITTEN_RUNNER.md (five-axis comparison vs a hand-written Python runner — concedes the token point on baseline B).
Important: every percentage / multiplier above is vs baseline A (prompt-loop) or labeled with its baseline pair. Against baseline B (hand-optimized runner with LLM only at judgment gates), the irreducible token win is ~1.3–1.5× on routing only — see
VS_HAND_WRITTEN_RUNNER.md. Against baseline C (pure deterministic, no LLM in loop), it is ~0%.
The reason: AINL compiles your workflow once. The runtime executes it deterministically — no LLM re-generation on each run for graph routing and adapter orchestration. The model authors the graph once; the runtime runs it on every invocation. That mechanism produces token savings only when the counterfactual was actually re-prompting on every run.
Token savings breakdown and benchmarks → ·
BENCHMARK.md(source tables + methodology) ·docs/CLAIMS_AND_EVIDENCE.md(claim crosswalk) · When AINL does not help →
We classify every public evidence row by source so reviewers can tell field reports from modeled scenarios:
We do not yet have a Class (a) deployment publicly committed. If your team would consider being the first, the pilot kit (tracked T2.5) is small. Until then we ask reviewers to read WHEN_AINL_DOES_NOT_HELP.md first, run the benchmarks, and judge on the published Class (b)/(c) evidence with the baseline qualifier attached.
Here for the programming language itself?
AINL is a compact, graph-canonical AI workflow language. You write programs in .ainl files, compile them to a deterministic IR graph, and execute them without prompt loops.
This GitHub repo is the technical source of truth for AINL: compiler, runtime, canonical graph IR, CLI, HTTP runner, MCP server, docs, examples, and conformance suite. For the high-level product story, use cases, and commercial/enterprise paths, visit ainativelang.com.
Full boundary details:
docs/OPEN_CORE_DECISION_SHEET.md
Vulnerability reporting and sensitive areas (outbound HTTP, the a2a adapter, secrets): see SECURITY.md. A2A-specific policy and wire contract: docs/integrations/A2A_ADAPTER.md.
Agentic HTTP payments & commerce (x402, MPP, AP2, ACP, AGTP): integration hub docs/integrations/README.md — HTTP-402 rails on the http adapter (HTTP_MACHINE_PAYMENTS.md), practitioner readiness (AGENTIC_PROTOCOLS_PRACTITIONER_READINESS.md), and AGTP options (AGTP.md).
ainl_step_examples; ainl_get_started with wizard_state_json for session continuity; MCP resource ainl://strict-valid-families (mined corpus/strict_valid_family_index.json, tooling/corpus_mining.py); ainl_validate / ainl_compile responses include contract_validation_status and contract_alignment.mismatched_calls (lightweight drift vs ADAPTER_CONTRACTS); tooling/mcp_exposure_profiles.json registers the wizard tool + family resource on design_impact_first, inspect_only, safe_workflow, and full. Hub: docs/operations/MCP_AINL_WIZARD_AND_CORPUS.md. ArmaraOS pairs with mcp:ainl:wizard_state graph facts and mcp_ainl_wizard_state_hint in the system prompt (see armaraos/docs/mcp-a2a.md).http adapter payment_profile (none/auto/x402/mpp) with structured 402 payment_required + http_payment frame merges; CLI --http-payment-profile / --http-max-payment-rounds; runner + MCP adapters.http keys. Docs: docs/integrations/HTTP_MACHINE_PAYMENTS.md, hub docs/integrations/README.md.a2a — wire profile 1.0 (GET …/.well-known/agent.json, tasks/send / tasks/get); allow_hosts / optional strict_ssrf / redirects off by default; enable via --enable-adapter a2a and --a2a-allow-hosts, or adapters + adapters.a2a. MCP exposure profiles do not enable a2a without adapters (see tooling/mcp_exposure_profiles.json + docs/integrations/A2A_ADAPTER.md). Tests: tests/test_a2a_adapter.py, tests/test_a2a_adapter_integration.py; example: examples/compact/a2a_delegate.ainl.pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json, mirrored emit server engine aligned to 1.7.1 for that tag's PyPI publish (see docs/CHANGELOG.md § v1.7.1, docs/RELEASE_NOTES.md; Known limitations point at A2A_ADAPTER: TOCTOU, empty allowlist, IDNA).MemoryNode fields vitals_gate, vitals_phase, vitals_trust; Rust snapshot import; inbox schema + tests/test_vitals_bridge.py — keeps Python graph store / inbox aligned with ArmaraOS Rust EpisodeNode vitals (pair with current ArmaraOS for patch inbox drain on the Rust side).ainl-* + OpenFang): integration contracts and docs now explicitly track the ainl-runtime/openfang-runtime/openfang-kernel/openfang-types path used in production ArmaraOS builds, including optional ainl-runtime-engine turn routing, internal delegation-depth guards, and shared graph-memory session semantics for mixed Python/Rust deployments.PatchAdapter / AdapterRegistry dispatch with GraphPatchAdapter host forwarding is now documented alongside Python GraphPatch so label-keyed procedural patches can converge on a single cross-runtime contract while Python remains the rich memory.patch executor.ainl-persona-evolution, ainl-extractor, ainl-tagger) and runtime gates (AINL_PERSONA_EVOLUTION, AINL_EXTRACTOR_ENABLED, AINL_TAGGER_ENABLED) that back ExtractionReport phase warnings and graph-memory enrichment across the Rust and Python boundary.schema_version: ainl emit --target armaraos writes schema_version on HAND.toml, IR JSON, and security.json — tests/test_emit_armaraos_handpack.py.build_armaraos_monitor_registry, boot_armaraos_graph_memory, CronDriftCheckAdapter, tests/test_armaraos_monitor_registry.py.AdapterRegistry.get; graph-patch uses adapters.get("ainl_graph_memory").pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json, mirrored emit server engine bumped to 1.7.0 for that tag's PyPI publish (superseded by v1.8.0 in this tree — see New in v1.8.0 above; PyPI shows 1.8.0 only after that release is uploaded — docs/RELEASING.md).R memory.patch (and graph memory.patch) installs procedural label bodies from the JSON graph store via ainl_graph_memory.graph_patch, with compile-time strict literal checks, runtime dataflow validation (_analyze_step_rw), overwrite protection for compiled labels, boot-time _reinstall_patches, and per-label fitness EMA (including early J exits). Tests: tests/test_graph_patch_op.py.PatchAdapter registry + GraphPatchAdapter fallback), creating a stable integration seam that v1.7.0 extended through vitals, extractor, persona, and semantic-tagging convergence, and that v1.7.1 extended with the opt-in a2a (Agent-to-Agent) network adapter — v1.8.0 layers MCP authoring depth (wizard, corpus index, contract alignment) and HTTP 402 payment profiles on http.pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json, mirrored emit server engine, and ADAPTER_REGISTRY.json / docs/reference/ADAPTER_REGISTRY.md aligned to 1.6.0.memory.patch) promotes proven behavior into reusable procedural graph structure under strict dataflow and overwrite guards.PatchAdapter / GraphPatchAdapter) are intentionally aligned to support one portable graph-memory model across both stacks.LATE_NIGHT_CONVO_WITH_AI.md, WHITEPAPERDRAFT.md, and ArmaraOS prior-art lineage in sbhooley/armaraos/PRIOR_ART.md.memory_type on compiled R steps; typed emit_edges + tooling/graph_api helpers (emit_edges, data_flow_edges, memory_nodes); memory.pattern_recall + __last_pattern__ for procedural memory.merge round-trips — docs/architecture/GRAPH_INTROSPECTION.md, docs/adapters/AINL_GRAPH_MEMORY.md.persona.load injects graph-store traits into the execution frame; memory / persona graph ops registered for strict validation — examples/persona_demo.ainl, tests/test_persona_load_engine.py, tests/test_strict_adapter_contracts.py.AINLBundle / AINLBundleBuilder (runtime/ainl_bundle.py) round-trip workflow IR + memory + persona + tool strings to .ainlbundle JSON — tests/test_ainl_bundle.py.ainl_mcp_limits.json warnings on successful runs; invalid workspace cache.json → adapter_config_error during MCP auto-cache; max_adapter_calls: 0 enforced at the first adapter dispatch.security.json capability_declarations.adapters; HAND.toml ainl_ir_version.pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json, and mirrored emit server engine aligned to 1.5.2.WHITEPAPERDRAFT.md v1.5.2 + §6.8 (graph-memory gap audit narrative).MemoryRecall / MemorySearch dispatch the ainl_graph_memory adapter (ArmaraOS JSON graph store); see docs/adapters/AINL_GRAPH_MEMORY.md, tests/test_memory_recall_op.py (dispatch contract), and tests/test_memory_search_op.py (search + temp GraphStore).armaraos/bridge/ainl_graph_memory.py, runner registration + delegation hook, optional graph_viz server, demo/procedural_roundtrip_demo.py, demo/ainl_graph_memory_demo.py (graph-memory walkthrough + export), token-budget bridge shim (bridge_token_budget_adapter.py).pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json, and mirrored emit server engine aligned to 1.5.1.ainl_graph_memory appears in tooling/adapter_manifest.json, ADAPTER_REGISTRY.json, and tooling/effect_analysis.py (ADAPTER_EFFECT) alongside the human registry in docs/reference/ADAPTER_REGISTRY.md.RUNTIME_VERSION, CITATION.cff, and tooling/bot_bootstrap.json aligned with PyPI ainativelang 1.5.0 (see docs/CHANGELOG.md § v1.5.0).apollo-x-bot/api-cost-monitor.ainl (promoter / API-cost workflow sample), demo/test_openspace_http.ainl (experimental OpenSpace HTTP probe), and run_openspace_test.py (portable dev harness for demo/test_openspace_mcp.ainl — no hard-coded workspace paths).ainl install-mcp --host armaraos: merges env pass-through (AINL_MCP_EXPOSURE_PROFILE, tools/resources allow/deny lists) into existing [[mcp_servers]] name = "ainl" blocks so upgrades do not require hand-editing ~/.armaraos/config.toml.ainl-mcp): ainl://authoring-cheatsheet resource, process-local validate telemetry, and tighter validate/compile integration for agent-facing diagnostics.contract_violation_reason on include-related diagnostics, and targeted exemptions for labels whose last step is inner Loop / While (fewer false strict failures on assembly-style pipelines).ainativelang 1.4.4: version surfaces aligned (pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json).emit_solana_client header now uses live RUNTIME_VERSION so generated clients never drift from the installed runtime.core.* builtins expanded: EQ/NEQ/GT/LT/GTE/LTE comparisons, TRIM/STRIP/LSTRIP/RSTRIP whitespace, STARTSWITH/ENDSWITH, KEYS/VALUES, STR/INT/FLOAT/BOOL coercions — all now implemented in runtime/adapters/builtins.py. These verbs were already in the validator contract; now they work at runtime too.ainl_compile returns frame_hints[]: list of {name, type, source} entries so agents can auto-construct the frame parameter before calling ainl_run. Add # frame: name: type comment lines to source for authoritative hints (# frame: name alone is allowed and yields type: "any").ainl_mcp_limits.json in the fs.root directory to tune max_steps/max_time_ms/max_adapter_calls per workspace without editing global server config. Invalid JSON in that file is ignored for limit purposes; successful ainl_run responses may include a warnings entry. max_adapter_calls: 0 blocks all adapter dispatches (first R fails with a structured runtime error).fs is enabled and cache is not explicitly listed in adapters.enable, the MCP server registers cache against output/cache.json or cache.json under fs.root if that file exists; non-empty files must be valid JSON. See docs/operations/MCP_RESEARCH_CONTRACT.md and tests tests/test_mcp_auto_cache_adapter.py, tests/test_mcp_workspace_limits.py, tests/test_mcp_frame_hints.py, tests/test_emit_armaraos_handpack.py.ainl_run adapters parameter for scoped http, fs, cache, sqlite per call._SERVER_DEFAULT_LIMITS in runtime_runner_service.py raised to match MCP defaults (max_steps: 500000, max_adapter_calls: 50000, max_time_ms: 900000).AINL_ALLOW_IR_DECLARED_ADAPTERS relaxes env AINL_HOST_ADAPTER_ALLOWLIST when set; intelligence paths under intelligence/ opt in by default unless AINL_INTELLIGENCE_FORCE_HOST_POLICY=1.ainl run registers web, tiktok, queue; MCP ainl_run grants match the HTTP runner; capabilities document host security env (see docs/LLM_ADAPTER_USAGE.md).J) graphs; effect_analysis / adapter_manifest coverage for web, tiktok, svc, crm, and expanded core verbs; intelligence examples use R queue Put and valid prelude layout; demo/.ainl-library-skip excludes dev demos from ArmaraOS App Store listings.offline): deterministic AbstractLLMAdapter for config.yaml + register_llm_adapters demos and CI; use in llm.fallback_chain without live API keys (see fixtures/llm_offline.yaml).05b_unified_llm_offline_config.ainl — unified llm path vs llm_query mock in 05_route_then_llm_mock.ainl; parser-compat runs strict wishlist validation + no-network smoke for graphs 01 and 05b.core.GET: real R target on CoreBuiltinAdapter (deep key/index reads via deep_get); strict entries in tooling/effect_analysis.py alongside llm.COMPLETION.LLMRuntimeAdapter normalizes verb casing so R llm.COMPLETION matches registry verbs (e.g. completion).ainl emit --target armaraos (hand package: HAND.toml, <stem>.ainl.json, security.json, README), ainl status --host armaraos (canonical ARMARAOS_* + legacy OPENFANG_* env), ainl install-mcp --host armaraos ([[mcp_servers]] in ~/.armaraos/config.toml, ~/.armaraos/bin/ainl-run, PATH hints).pyproject.toml, RUNTIME_VERSION, CITATION.cff, tooling/bot_bootstrap.json; ainl serve GET /health reports version from RUNTIME_VERSION.docs/ARMARAOS_INTEGRATION.md, host hub docs/getting_started/HOST_MCP_INTEGRATIONS.md; integration tests and emitter import path fixes.--enhanced-diagnostics): graph context + Mermaid snippets on compile errors.ainl visualize --highlight-errors): error nodes styled in Mermaid output.--estimate on check, inspect, status): per-node token/USD estimates.--enable-adapter audit_trail --audit-sink file:///...): immutable JSONL compliance log (graph must invoke audit_trail.record).ainl_preprocess.py): Python-like compact .ainl authoring alongside opcodes — same IR, fewer surface tokens; see examples/compact/ and AGENTS.md.Full version history: docs/CHANGELOG.md · docs/RELEASE_NOTES.md
AINL helps turn AI from "a smart conversation" into "a structured worker."
v1.3.3 — Native Solana + prediction markets: See
docs/solana_quickstart.mdfor strict graphs, env vars, dry-run-first flows, and--emit solana-client/blockchain-clientusage, plusexamples/prediction_market_demo.ainlfor a concrete resolution → conditional payout pattern.
DERIVE_PDA with single-quoted JSON seeds, GET_PYTH_PRICE (legacy + PriceUpdateV2), HERMES_FALLBACK, and INVOKE / TRANSFER_SPL with explicit priority fees (micro-lamports per CU).AINL_DRY_RUN=1) and emitted standalone clients via --emit solana-client so you can rehearse flows before sending real transactions.docs/solana_quickstart.md and examples/prediction_market_demo.ainl.All Solana additions are additive-only and preserve full Hyperspace compatibility.
AINL provides the deterministic, capability-declared graph layer. Pair it with Hyperspace AVM (avmd) or general runtimes (Firecracker microVMs, gVisor, Kubernetes Agent Sandbox, E2B-style runtimes, AVM Codes platform) for stronger isolation.
execution_requirements in compiled IR (avm_policy_fragment, isolation/resource hints).ainl generate-sandbox-config <file.ainl> [--target avm|firecracker|gvisor|k8s|general].runtime/sandbox_shim.py auto-detects AVM/general sandbox endpoints and falls back cleanly.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.
Compile-once, run-many: you author (or import) a graph once; the runtime executes it deterministically without re-spending LLM tokens on orchestration each time. Size economics are tracked with tiktoken cl100k_base; the viable subset (e.g. public_mixed) shows about ~1.02× leverage for minimal_emit vs unstructured baselines—see BENCHMARK.md, docs/benchmarks.md, and docs/architecture/COMPILE_ONCE_RUN_MANY.md.
Performance & benchmarks (updated Mar 2026): Size results use tiktoken cl100k_base (billing-aligned for GPT-4o–class models). Reports separate viable subset rows from legacy-inclusive aggregates; minimal_emit fallback stub and emitter compaction (e.g. prisma / react_ts stubs) are documented in the transparency blocks. See BENCHMARK.md for tables; narrative hub docs/benchmarks.md (highlights, commands, CI). Runtime economics and optional reliability batches: tooling/benchmark_runtime_results.json via make benchmark / scripts/benchmark_runtime.py. For long-lived OpenClaw deployments, pair these static benchmarks with live token-budget observability and cost tracking via docs/operations/TOKEN_AND_USAGE_OBSERVABILITY.md and the monitoring components documented in docs/MONITORING_OPERATIONS.md.
These commands are implemented in cli/main.py and documented in docs/agents/openclaw-operator.md. For bots and IDE tools, tooling/bot_bootstrap.json exposes the same surface under openclaw_commands (plus ai_native_lang_example_yml). Project lock example files: aiNativeLang.example.yml (repo root) and tooling/aiNativeLang.example.yml (packaged wheels).
The CLI fails fast if tests/emits/server/server.py is missing (typical for PyPI-only installs), with the same run_tests_and_emit hint.
Shell shortcut: scripts/setup_ainl_integration.sh delegates to ainl install openclaw (supports --dry-run, --workspace, --verbose).
Requires Python 3.10+. No git clone needed to try it.
# 1. Install the CLI
pip install ainativelang
# 2. Create a new project (generates main.ainl + README)
ainl init my-first-worker
cd my-first-worker
# 3. Check the program compiles cleanly (strict graph semantics)
ainl check main.ainl --strict
# 4. Run it
ainl run main.ainl
# 5. Visualise the control-flow graph
ainl visualize main.ainl --output - # paste into https://mermaid.live
That's it. Edit main.ainl, add adapter calls (cache, HTTP, LLM, memory), revalidate, run again.
The ainl init command creates a clean, well-commented main.ainl designed for newcomers. It demonstrates core concepts — graph labels (L1: = control-flow node), requests (R cache get = read from the cache adapter), joins (J = return a value and finish the node), and branching — while remaining production-ready. Open main.ainl after scaffolding; the comments tell you exactly what each line does.
AINL now supports a human-friendly compact syntax alongside the original opcodes. Both compile to the same IR. Compact is recommended for new code — 66% fewer tokens.
# examples/compact/hello_compact.ainl
adder:
result = core.ADD 2 3
out result
# Branching, inputs, adapter calls, cron — all work
classifier:
in: level message
severity = llm.classify level message
if severity == "CRITICAL":
http.POST ${SLACK_WEBHOOK} {text: message}
out "alerted"
out "logged"
See examples/compact/ for more, and AGENTS.md for the full compact syntax reference.
.ainl program.ainl validate your.ainl --strict
Or the equivalent: ainl check your.ainl --strict
Failures include structured diagnostics (line, suggestion, optional llm_repair_hint).
Use --json-diagnostics for CI/machine-readable output.ainl visualize your.ainl --output - > graph.mmd — paste into mermaid.live.ainl run your.ainlainl emit your.ainl --target langgraph -o graph.pyainl serve --port 8080 (POST /validate, /compile, /run)ainl inspect your.ainl --strictainl run your.ainl --trace-jsonl run.trace.jsonl# Clone and create an isolated env (match CI: Python 3.10)
git clone https://github.com/sbhooley/ainativelang.git
cd ainativelang
PYTHON_BIN=python3.10 VENV_DIR=.venv-py310 bash scripts/bootstrap.sh
source .venv-py310/bin/activate # Windows: .venv-py310\Scripts\activate
# Install with dev + web extras
python -m pip install --upgrade pip
python -m pip install -e ".[dev,web]"
# Validate an example
ainl check examples/hello.ainl --strict
# Run the core test suite
python scripts/run_test_profiles.py --profile core
# Environment diagnostics
ainl doctor
# Full conformance matrix
make conformance
# Runner service (for API/orchestrator integration)
python scripts/runtime_runner_service.py
# GET http://localhost:8770/capabilities
# POST http://localhost:8770/run {"code": "S app api /api\nL1:\nR core.ADD 2 3 ->sum\nJ sum"}
See docs/INSTALL.md and CONTRIBUTING.md for full contributor setup.
For self-improving loops (generate -> inspect -> mutate -> evaluate), use:
ainl inspect candidate.ainl --strictainl_ir_diff(file1, file2, strict=true)ainl_fitness_report(file, runs=5, strict=true)ainl_validate diagnostics include llm_repair_hintContract and stable payload fields: docs/operations/MCP_RESEARCH_CONTRACT.md.
For the full conformance matrix in one command (tokenizer, IR canonicalization, strict validation, runtime parity, emitter stability):
make conformance (or SNAPSHOT_UPDATE=1 make conformance when intentionally updating snapshots).
GROWTH-PLAN.mddocs/validation-deep-dive.mdShort primer for stakeholders: docs/WHAT_IS_AINL.md (canonical). WHAT_IS_AINL.md at repo root is a stub that points to the same content.
Pull in shared subgraphs from modules/ (paths resolve next to your source file, then CWD, then ./modules/):
include "modules/common/retry.ainl" as retry
L1: Call retry/ENTRY ->out J out
See Includes & modules below for timeout.ainl, strict rules, and the starter table.
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.
Deeper setup: See docs/INSTALL.md for platform-specific install, Docker, and pre-commit setup.
Import Clawflows-style WORKFLOW.md or Agency-Agents-style personality Markdown into a deterministic .ainl graph (cron trigger, sequential Call steps or agent gates, optional memory / queue hooks for OpenClaw-style bridges). If structured parsing cannot extract steps or agent fields, the importer falls back to a compiling minimal_emit fallback stub (Phase‑1 style) so you still get valid, reviewable graph source.
Host quick links: OpenClaw · ZeroClaw skill (AINL) · Hermes Agent · ArmaraOS — AINL wiring for all four is in docs/getting_started/HOST_MCP_INTEGRATIONS.md (ainl install-mcp --host openclaw|zeroclaw|hermes|armaraos).
The same path is exposed over MCP as ainl_list_ecosystem, ainl_import_clawflow, ainl_import_agency_agent, and ainl_import_markdown (stdio ainl-mcp). Weekly auto-sync ( .github/workflows/sync-ecosystem.yml ) refreshes examples/ecosystem/ from upstream public Markdown; community additions use .github/PULL_REQUEST_TEMPLATE/ (workflow / agent templates).
ainl import markdown https://raw.githubusercontent.com/nikilster/clawflows/main/workflows/available/community/check-calendar/WORKFLOW.md \
--type workflow -o morning.ainl
ainl compile morning.ainl
Agent imports support --personality "…" and optional --generate-soul (writes SOUL.md and IDENTITY.md next to -o). Use --no-openclaw-bridge to emit cache instead of memory / queue.
Shortcuts (fetch five samples from upstream into examples/ecosystem/ — requires network):
ainl import clawflows
ainl import agency-agents
zeroclaw skills install https://github.com/sbhooley/ainativelang/tree/main/skills/ainl
This installs the AINL importer, runtime shim, and MCP tools directly into ZeroClaw.
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.
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 ….)
Details: docs/ZEROCLAW_INTEGRATION.md · skill files: skills/ainl/README.md.
OpenClaw uses npm + openclaw onboard for the host CLI. AINL is added as a skill folder (not via zeroclaw skills install): copy skills/openclaw/ to ~/.openclaw/skills/ or <workspace>/skills/, or install from ClawHub when the skill is listed there.
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.
Once 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 BENCHMARK.md compile-once/run-many scenarios + scripts/benchmark_compile_once_run_many.py).
For restricted Python sandboxes (PEP 668 externally-managed environments, common on OpenClaw/Clawbot hosts), no-root install order is: venv first, then --user, then --break-system-packages only as a last resort. skills/ainl/install.sh runs a compatible fallback sequence automatically and continues with MCP setup once ainl is available.
Intelligence layer (after bootstrap): install-mcp / ./install.sh wires MCP and ainl-run; bridge cron, env profiles, and run_intelligence still need the one-time operator pass in docs/operations/OPENCLAW_AINL_GOLD_STANDARD.md. With that wiring, the OpenClaw bridge + intelligence path exposes AINL’s cap auto-tuner, rolling budget → monitor hydration, and optional embedding pilot—a self-managing resource & budget layer (not self-tuning workflow logic: compiled graphs stay deterministic) that adjusts caps and cache pressure from observed usage. See docs/INTELLIGENCE_PROGRAMS.md and docs/operations/TOKEN_AND_USAGE_OBSERVABILITY.md. On typical high-frequency monitoring and digest workloads, that stack helps sustain ~90–95% token savings versus prompt-loop orchestration for the same scheduled work, with near-zero recurring orchestration cost after compile—validate on your host (ainl bridge-sizing-probe, weekly trends).
If you need a clean uninstall in managed sandboxes:
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*
Try in chat: “Import the morning briefing using AINL.”
Details: docs/OPENCLAW_INTEGRATION.md · skill files: skills/openclaw/README.md.
Standalone skill repo (optional, later): publish the contents of skills/openclaw/ as the root of github.com/sbhooley/ainl-openclaw-skill so users can clone or vendor a single-purpose tree (same three files: SKILL.md, install.sh, README.md).
Hermes Agent is a skill-native runtime with a closed learning loop. AINL pairs deterministic compiled graphs with Hermes via ainl-mcp (ainl_run) and --emit hermes-skill bundles (agentskills-style SKILL.md + workflow.ainl + ir.json).
Bootstrap: pip install 'ainativelang[mcp]' then ainl install-mcp --host hermes (alias ainl hermes-install), or run skills/hermes/install.sh. Emit skills to ~/.hermes/skills/ainl-imports/<name>/.
Details: docs/HERMES_INTEGRATION.md · hub one-pager: docs/integrations/hermes-agent.md · skill pack: skills/hermes/README.md.
Curated templates with original.md, converted.ainl, and notes: examples/ecosystem/README.md.
Weekly auto-sync: the repo can refresh those sample trees from upstream on a schedule via GitHub Actions — see .github/workflows/sync-ecosystem.yml (Monday 04:00 UTC, plus manual workflow_dispatch). PRs are opened only when examples/ecosystem/** conversions change. That workflow also creates the GitHub labels ecosystem, automation, workflow, and agent if missing (idempotent), then applies ecosystem + automation to the sync PR. If your org disallows GITHUB_TOKEN from opening PRs, set repository secret GH_PAT (PAT with repo + PR access to this repo only); see docs/ECOSYSTEM_OPENCLAW.md — no access to upstream Clawflows/Agency-Agents orgs is required (public raw fetches only).
After you push a branch, open a pull request on GitHub and use the template dropdown to choose Submit Workflow (Clawflows-style) or Submit Agent (Agency-Agents-style) (see .github/PULL_REQUEST_TEMPLATE/).
You can also append ?quick_pull=1&template=workflow-submission.md or template=agent-submission.md to your compare URL (main…your-branch).
Templates: workflow-submission.md · agent-submission.md · default pull_request_template.md.
modules/efficient_styles.ainlAINL ships a reusable output style module that routes user-facing responses through a dense, professional prose style and tool/agentic steps through structured JSON — eliminating redundancy at the LLM output layer.
include "modules/efficient_styles.ainl" as style
my_workflow:
in: question
# ... do work ...
result = core.GET work_result
if is_user_facing:
out = style.human_dense_response result
out = style.terse_structured result
human_dense_response — natural English, full paragraphs, examples where helpful. Strips hedging (I think, basically), redundancy, pleasantries. Code, numbers, steps remain 100 % exact and detailed.
terse_structured — JSON-only output for tool steps and internal state. Never use for end-user responses.
When combined with the ArmaraOS Ultra Cost-Efficient Mode input compressor (heuristic input reduction in Rust, under 30 ms target; typical ~40–56 % input savings in Balanced mode on conversational text), using this module on output as well stacks savings on both sides of the LLM. Total bill impact depends on your input/output token mix and model pricing (e.g. Claude Sonnet 4.6 list $3/M input · $15/M output).
Cross-repo reference: docs/operations/EFFICIENT_MODE_ARMARAOS_BRIDGE.md — how CLI env, efficient_styles.ainl, and ArmaraOS docs/prompt-compression-efficient-mode.md relate.
CLI hint for ArmaraOS-hosted graphs (sets AINL_EFFICIENT_MODE env var — Rust compression is on the host):
ainl run my_workflow.ainl --efficient-mode balanced
Note: the --efficient-mode flag only signals the ArmaraOS kernel via environment. No compression runs in Python — implementation is in openfang-runtime (prompt_compressor).
Reuse battle-tested patterns without copy-pasting whole graphs. Compile-time include merges each module’s labels under alias/LABEL keys (for example retry/ENTRY, retry/EXIT_OK, timeout/WORK).
Syntax (paths resolve next to the source file, then the current working directory, then ./modules/):
include "modules/common/retry.ainl" as retry
include modules/common/timeout.ainl as timeout
Quotes around the path are optional when unambiguous; as alias sets the prefix for every label from that file.
Prelude order: put every include line before the first top-level S or E (service / endpoint). Lines after S / E are not part of the include prelude; modules merged too late will not expose Call alias/… targets. See modules/common/README.md.
include "modules/common/retry.ainl" as retry
include "modules/common/timeout.ainl" as timeout
S app api /api
L1: Call retry/ENTRY ->r J r
L2: Call timeout/ENTRY ->t J t
Subgraphs must define LENTRY: (merged as alias/ENTRY) and at least one LEXIT_*: label in strict mode. Do not declare top-level E / S inside includes—endpoints and services belong in the main program. Use quoted jumps for string payloads (J "ok") so strict dataflow treats them as literals.
Shared modules live in a modules/ directory next to your files (with CWD / ./modules/ fallback—see compiler path resolution).
Starter modules in this repo
modules/common/)retry.ainl — exponential backoff + max retriestimeout.ainl — timeout wrapper with placeholder delay (swap to real timer later)include "modules/common/timeout.ainl" as timeout
L1:
Call timeout/ENTRY ->out
J out
More patterns coming soon (approval gate, circuit breaker, RAG retrieval, etc.). Contract (strict): included subgraphs expose LENTRY: (merged as alias/ENTRY) and at least one LEXIT_*: exit label; call them with Call alias/ENTRY ->out from the parent. Agents benefit from smaller, verified building blocks and stable qualified names (retry/n1, …) in the graph IR. Full behavior, path resolution, and tests: tests/test_includes.py, docs/architecture/GRAPH_INTROSPECTION.md.
See your includes in a diagram: ainl visualize main.ainl -o graph.mmd — each alias becomes a Mermaid subgraph cluster; synthetic Call → edges into alias/ENTRY are annotated in the output.
executor_request_builder, record_decision, and KV snapshot hooks: apollo-x-bot/README.md. Optional Growth Pack (v1.3) (follow/discovery/like/thread/awareness, env-gated) is documented in the same README under Optional Apollo-X Growth Pack.AINL can be used through three integration surfaces. All three run the same compiler and runtime; they differ in how you connect.
External runtime option (opt-in): AINL can call PTC-Lisp through ptc_runner
for reliability overlays and trace interoperability; see docs/adapters/PTC_RUNNER.md.
The canonical "hello world" workflow used below:
S app api /api
L1:
R core.ADD 2 3 ->x
J x
# Validate and inspect IR
ainl-validate examples/hello.ainl --strict --emit ir
# Mermaid diagram (paste into mermaid.live)
ainl visualize examples/hello.ainl --output - > hello.mmd
# Run directly
ainl run examples/hello.ainl --json
No server needed. Good for local development, scripting, and CI.
# Start the runner service
ainl-runner-service
# default: http://localhost:8770
# Discover capabilities
curl http://localhost:8770/capabilities
# Execute a workflow
curl -X POST http://localhost:8770/run \
-H "Content-Type: application/json" \
-d '{"code": "S app api /api\nL1:\nR core.ADD 2 3 ->x\nJ x", "strict": true}'
Best for container deployments, sandbox controllers, and external orchestrators.
See docs/operations/EXTERNAL_ORCHESTRATION_GUIDE.md.
# Install with MCP extra
pip install -e ".[mcp]"
# Start the stdio MCP server
ainl-mcp
Then configure your MCP-compatible host (Gemini CLI, Claude Code, Codex, etc.)
to use the ainl-mcp stdio transport. The host can call ainl_validate,
ainl_compile, ainl_capabilities, ainl_security_report, and ainl_run.
MCP v1 runs with safe defaults (core-only adapters, conservative limits).
Operators can scope which tools/resources are exposed via named exposure
profiles (AINL_MCP_EXPOSURE_PROFILE) or env-var inclusion/exclusion lists.
See section 9 of docs/operations/EXTERNAL_ORCHESTRATION_GUIDE.md for the
full quickstart, exposure scoping, and gateway deployment guidance.
Three layers: MCP exposure profile → what tools/resources the host can discover. Security profile / capability grant → what execution is allowed. Policy / limits → what each run is constrained by.
For Claude Code / Cowork / Dispatch users: Treat AINL as a scoped MCP tool provider and deterministic workflow/runtime layer underneath your host. Start with
validate_onlyorinspect_onlyexposure profiles, and only enablesafe_workflowafter operators have reviewed security profiles, grants, policies, limits, and adapter exposure. AINL is not the host, not Cowork, not a gateway, and not a control plane. For a concrete validator → inspector → safe-runner walkthrough, see the End-to-end example section ofdocs/operations/EXTERNAL_ORCHESTRATION_GUIDE.md.
Core first, advanced later. The paths above use the core compiler and runtime only. Advanced/operator-only surfaces (agent coordination, memory migration, OpenClaw extensions) are documented separately under
docs/advanced/and are not the recommended starting point for new users.
For the full getting-started guide, see docs/getting_started/README.md.
Modern AI systems are increasingly powerful at reasoning, but still unreliable and expensive when forced to orchestrate whole workflows through long prompt loops. Long prompt loops create:
AINL addresses this by moving orchestration out of the model and into a deterministic execution substrate:
flowchart LR
A[AINL Source] --> B[Compiler]
B --> C[Canonical Graph IR]
C --> D[Runtime Engine]
D --> E[Adapters / Tools / State]
D --> F[Optional LLM Calls]
The graph is the source of truth. The runtime is the orchestrator. The model is a bounded reasoning component inside the system.
AINL programs compile to canonical graph IR. Execution follows graph semantics, not ad hoc conversational state.
The surface language is intentionally compact and structured for parseability, determinism, and low-entropy generation by models.
AINL's strict mode enforces high-value invariants such as:
Strict validation is paired with structured diagnostics (native Diagnostic records: lineno, spans, kinds, suggested fixes) surfaced on the CLI with rich or plain text, or JSON for automation (ainl-validate, ainl visualize, language server). See docs/INSTALL.md and docs/CONFORMANCE.md.
AINL describes what should happen. Adapters implement how it happens. This allows the same graph language to drive HTTP, SQLite, filesystem operations, email/calendar/social integrations, service checks, cache/memory, queues, WASM modules, and OpenClaw-specific operational workflows.
PTC-style overlays are additive and opt-in:
ptc_runner for external PTC-Lisp execution (R ptc_runner run ...)llm_query for ad-hoc LLM calls in graph steps# signature: ... metadata with runtime checks via intelligence/signature_enforcer.py_-prefixed context firewall at adapter/export serialization boundariesintelligence/trace_export_ptc_jsonl.pyOne AINL program can describe a workflow once and emit multiple downstream artifacts (FastAPI, React/TypeScript, Prisma, OpenAPI, Docker/Compose, Kubernetes, cron/queue/scraper outputs), rather than forcing an agent to regenerate parallel implementations.
Emitters: --emit hyperspace via python3 scripts/validate_ainl.py … writes hyperspace_agent.py (use -o path). It embeds the compiled IR and runs it with RuntimeEngine, registers vector_memory / tool_registry, optional hyperspace_sdk import stub, and respects AINL_LOG_TRAJECTORY for SOURCE_STEM.trajectory.jsonl in the current working directory.
Hyperspace happy path (use --enable-adapter vector_memory and --enable-adapter tool_registry with ainl run when the graph calls those adapters). After emit, run python3 demo_agent.py from repo root (or any working tree that contains runtime/engine.py and adapters/) so imports resolve:
ainl-validate examples/hyperspace_demo.ainl --strict --emit hyperspace -o demo_agent.py
cd /path/to/AI_Native_Lang && AINL_LOG_TRAJECTORY=1 python3 demo_agent.py
# optional: ainl run examples/hyperspace_demo.ainl --enable-adapter vector_memory --enable-adapter tool_registry --log-trajectory --json
Once a workflow is compiled, it executes repeatedly without needing the model to regenerate orchestration logic. Runtime state is handled by adapters. Recurring workflows avoid repeated prompt-loop costs.
AINL sits at the intersection of graph-native agent orchestration, deterministic workflow execution, and AI-native programming languages.
For a detailed comparison of graph-native vs prompt-loop architectures with production evidence, see docs/case_studies/graph_agents_vs_prompt_agents.md.
AINL uniquely combines:
→ Treating AI systems as deterministic programs, not prompt loops.
AINL is best suited for:
AINL is less optimized for casual chatbot prototyping, one-off prompt hacks, or no-code-first usage.
AINL matters when AI moves beyond demos and starts doing real operational work. It helps reduce the gap between "a clever AI demo" and "a workflow a business can actually run" — repeatable, inspectable, stateful, tool-using, cost-aware, and easier to validate and maintain.
An AINL program gives an agent explicit control flow, explicit side effects, compile-time validation, capability-aware boundaries, externalized memory, and reproducible runtime behavior. The LLM stops being the whole control plane and becomes a reasoning component inside a deterministic system.
AINL is not just a speculative language design. It is already used in live OpenClaw-integrated workflows.
The Apollo / OpenClaw stack exercises adapters such as email, calendar, social, db, svc, cache, queue, wasm, memory, extras, and tiktok.
Production-validated examples include:
demo/monitor_system.lang — recurring multi-module monitorThese programs demonstrate that AINL is effective for recurring monitors, stateful automation, autonomous ops, safety-aware tool orchestration, and long-lived agent systems.
AINL is most valuable when workflows are recurring, stateful, branching, safety-sensitive, multi-step, multi-target, or shared across teams or agents. For trivial one-off scripts, the gain is smaller. For multi-step agent systems and autonomous operational workflows, the gain can be substantial.
AINL's compactness and cost benefits should be described carefully.
scripts/benchmark_runtime.py, tooling/benchmark_runtime_results.json) measure post-compile latency, RSS, optional execution reliability batches, and tiktoken-based cost estimates—see docs/benchmarks.md.Bottom line: AINL lowers overall token usage while increasing capability, predictability, and reliability.
What is supported today:
BENCHMARK.md). Headline ratios use a viable subset for mixed profiles so representative workloads are not drowned out by tiny legacy shells; legacy-inclusive totals are printed separately for honesty.--strict-mode on scripts/benchmark_size.py enables true strict compilation (reachability pruning) for canonical_strict_valid only—see BENCHMARK.md callout when activeWhat is not supported:
Current benchmark framing:
canonical_strict_valid is the primary headline profile (19/19 viable example programs in tooling/artifact_profiles.json).--metric (default tiktoken). Legacy --metric=approx_chunks is optional and deprecated for billing claims.BENCHMARK.md, Mar 2026): make benchmark uses --mode wide: strict-valid ~3.2× full_multitarget_core (six compiler emitters) / ~362× full_multitarget (+ hybrid langgraph/temporal wrappers with embedded IR) / ~0.76× minimal_emit (tk). public_mixed viable 72/85; compatibility_only viable 53/66. Full detail: docs/benchmarks.md#benchmark-highlights-march-2026.prisma / react_ts benchmark stubs compacted Mar 2026 (~50–70% tk reduction on those emit lines); minimal_emit may add a small python_api fallback stub (~20–30 tk) when no selected target emits code—both are documented in BENCHMARK.md.full_multitarget, canonical strict examples show strong expansion leverage; runtime traces on the tracked benchmark JSON typically show 100% success on optional reliability batches for strict-valid workloads with sub-millisecond measured latency (machine-dependent).minimal_emit, mixed compatibility examples can be smaller or larger depending on artifact class and required targetsBENCHMARK.md with automation in make benchmark / make benchmark-ci and CI regression gating—see docs/benchmarks.md for the full map.# Refresh size markdown + JSON and runtime JSON (local).
# Uses `scripts/benchmark_size.py --mode wide` (core + full hybrid + minimal_emit).
make benchmark
# CI-style JSON only (does not rewrite BENCHMARK.md)
make benchmark-ci
Hybrid / LangGraph / Temporal optional deps: pip install -e ".[interop]" or ".[benchmark]" — see docs/PACKAGING_AND_INTEROP.md.
AINL provides a compact, reproducible, profile-segmented way to express graph workflows and multi-target systems, while often reducing repeated AI generation effort and avoiding repeated orchestration token burn during runtime.
AI Native Lang is an actively developed open-core project. The core compiler/runtime and graph tooling are real and usable; some language surfaces, examples, targets, and evaluation workflows are still being stabilized.
Public release expectations:
For implementation and shipped-capability status, see:
compiler_v2.pyruntime/engine.pycompiler_grammar.pytooling/http, sqlite, postgres, mysql, redis, dynamodb, airtable, supabase, fs, tools/run, /capabilities, health/metrics: scripts/runtime_runner_service.pytooling/adapter_manifest.json, tooling/security_profiles.jsontooling/security_report.pydocs/adapters/ADAPTER_TIERS.mddocs/runtime/TARGETS_ROADMAP.md as a capability map, not a promise that every target is equally production-ready.BENCHMARK.md, docs/OLLAMA_EVAL.md, and docs/TEST_PROFILES.md rather than as standalone proof of maturity.docs/WHAT_IS_AINL.md · root WHAT_IS_AINL.md (stub → docs)docs/solana_quickstart.md): WHITEPAPERDRAFT.mddocs/reactive/REACTIVE_EVENTS.md, examples/reactive/docs/reactive/ADVANCED_DURABILITY.mdtemplates/durability/templates/production/docs/integrations/EXTERNAL_EXECUTOR_BRIDGE.md · schemas/executor_bridge_request.schema.json · modules/common/executor_bridge_request.ainldocs/getting_started/README.mddocs/README.mddocs/AUDIENCE_GUIDE.mddocs/AINL_SPEC.mddocs/AINL_CANONICAL_CORE.mddocs/DOCS_INDEX.mddocs/benchmarks.mddocs/architecture/GRAPH_INTROSPECTION.mddocs/architecture/STATE_DISCIPLINE.mddocs/adapters/MEMORY_CONTRACT.md, docs/adapters/MEMORY_CONTRACT_V1_1_RFC.mdWorkflow memory is externalized through adapters (not the prompt). Production-style programs combine session or workflow namespaces, TTLs, bounded list filters, and prune so retention stays predictable under load. For a full OpenClaw-style illustration of cache + memory + budget enforcement (including audit rows and pruning hooks), see demo/session_budget_enforcer.lang. Optional access-aware touches (recency / frequency metadata on memory records) live in modules/common/access_aware_memory.ainl; use LACCESS_LIST_SAFE when you need list-wide touches under graph-preferred execution (see module header).
SEMANTICS.mddocs/RUNTIME_COMPILER_CONTRACT.mddocs/language/grammar.mddocs/CONFORMANCE.mddocs/EMBEDDING_RESEARCH_LOOPS.mddocs/operations/MCP_RESEARCH_CONTRACT.mddocs/operations/SANDBOX_EXECUTION_PROFILE.mddocs/operations/RUNTIME_CONTAINER_GUIDE.mddocs/operations/EXTERNAL_ORCHESTRATION_GUIDE.mddocs/INTEGRATION_STORY.mddocs/operations/AUTONOMOUS_OPS_PLAYBOOK.mdtooling/security_profiles.jsontooling/security_report.pydocs/advanced/SAFE_USE_AND_THREAT_MODEL.mddocs/operations/EXTERNAL_ORCHESTRATION_GUIDE.mdscripts/ainl_mcp_server.py (see external orchestration guide, section 9)docs/MONITORING_OPERATIONS.md and docs/INTELLIGENCE_PROGRAMS_INTEGRATION.mdAINL 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
總覽
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)
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Ainativelang 透過 stdio 在本機執行。
上次檢查時間:2026-10-27。 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)