AILANG Roadmap
This page is automatically generated from the design_docs/planned directory. Each item represents a planned feature or improvement with a detailed design document.
For completed features, see Design Documents.
Planned for v0.9.0
Planned for v0.8.0
- AILANG Demo: Invoice Processor with WebAssembly
- AILANG Execution Profiles — A Unified Architecture for Games, Agents, Services, and Tools
- Global Collaboration Hub - Cross-Computer Agent Collaboration
- Industry Vertical Examples - Sprint Plan
- Industry Vertical Example Projects for AILANG
- M-ARCH-BOUNDARIES: Formalize Dashboard/Core Separation
- M-ARCH1: AI Provider Base Class
- M-ARCH2: Daemon God Object Refactor
- M-ARCH3: Task Classification Consolidation
- M-ARCH4: Executor Stream Processor
- M-ARCH5: Error Handling Strategy
- M-CALL-SUGAR: Optional Parenthesized Call Syntax
- M-CLOUD-EVAL: Distributed Cloud Evaluation Workers
- M-CLOUD-INFRA: GCP Cloud Infrastructure for AILANG Services
- M-CLOUD-STORAGE: Cloud Database Migration
- M-CODEGEN-IR-STRATEGY: Multi-Layer IR Architecture for Code Generation
- M-CODEGEN-V3: Binding Hoisting for VALUE-Position Lets
- M-CONTRACTS-ASSERT: Contract-Based Preconditions
- M-COPILOT-CLI: GitHub Copilot CLI Integration
- M-CSP-SESSION-TYPES: CSP Concurrency with Session Types
- M-D4: Design-Doc-Driven Development (D4)
- Inline Tests Documentation & Examples (M-DX23)
- M-ENTROPY: Semantic Entropy Budgets
- M-ERROR-PROP: Error Propagation Operator (
?) - M-EVAL-UNIFIED-EXEC-CODEGEN: Unified Exec-Based Code Generation
- Sprint Plan: M-GENERIC-PIPELINE
- M-LOCOBENCH: Long-Context Benchmark Integration
- M-PERF3: Performance Quick Wins for 1.0.0
- M-QUASI: Typed Quasiquotes (String Templates)
- M-REFLECT: Structural Reflection & User-Defined Type Classes
- M-SEM-KERNEL: AILANG as a Symbolic Reasoning Kernel
- M-STRING-INTERP: String Interpolation Syntax
- M-VERIFY: SMT Verification & Redundant Generation (Phase 1-3)
- Semantic Caching: Future Work (v0.6.0+)
Planned for v0.7.2
- AILANG: Auto-Caps and Capability Inference
- M-REPL1: REPL Persistent Type Bindings & Module Loading
- M-TOOLING: Deterministic CLI for AI Agents (v0.3.15)
- M-UX2: Dev Experience Polish
- E2E Test: Coordinator Handoff Chains - Sprint Plan
- M-BUG-LETREC-SINGLE-CALL: Letrec with Single Recursive Call Fails
- M-CONTRACTS-OPLOWERING: Apply OpLowering to Contract Expressions
- M-COORD-THINKING: Extended Thinking Levels for Coordinator Skills
- Dashboard Simplification - Remaining Work (v0.7.0)
- Sprint Plan: M-DX24 - Developer Experience Improvements from BigQuery Connector Feedback
- M-DX24 Sprint Plan: Developer Experience Improvements
- Fix: Inline Tests Fail with Complex Imports
- Sprint Plan: Fix Inline Tests with Complex Imports
- M-DX26: Property Test "Empty Program" Bug
- M-DX27: GitHub Repository Search Fallback for
ailang docs search - M-EVAL-GAP: AILANG vs Python Parity Analysis
- M-EVAL-GAP-FIXES: Address Language Gaps from v0.7.0 Eval Analysis
- M-EXEC-HIERARCHY-REFACTOR: Executive Hierarchy Graph Visualization
- M-GEMINI-INTERACTIONS: Google Gemini Interactions API Support
- M-GEMINI-TRACE: Gemini CLI Trace Investigation
- M-PIPELINE-STANDALONE-EXPR: Standalone Expression Evaluation
- M-PROVENANCE: Code Provenance Tracing & Agent Trace Export
- Sprint Plan: M-STDLIB-GAPS
- Design Doc: M-STDLIB-GAPS - Standard Library Gap Analysis
- M-TASK-GRAPH-SPANS-UNIFICATION: Fix TaskHierarchyGraph Filtering
- M-TELEMETRY-HOOKS: Worktree Session Enrichment - Handoff Document
- M-TRACE-EXPORT: Execution Trace Export for AI Training
- M-UI-REFACTOR: Refactor UI Folder for AI-Friendly File Sizes
- Sprint Plan: M-UI-REFACTOR - AI-Friendly File Sizes
- M-WASM-REPL: Browser Module Loading for WASM REPL
- M-WASM-REPL Sprint Plan: Browser Module Loading
- M-WASM-STDLIB: Embed Standard Library in WASM Binary
- Sprint Plan: Test Chain Environment Propagation
- Test Chain Environment Propagation
- Test Chains Integration v2 - Sprint Plan
- Test Chains Integration v2
Long-term Vision
AILANG is designed as a deterministic language for autonomous AI code synthesis. The long-term roadmap includes:
- Structural Reflection - Typed quasiquotes and AST manipulation
- Schema Registry - Machine-readable type and effect definitions
- Capability Budgets - Resource-bounded effects
- Training Data Export - Execution traces for AI self-training
For the complete vision, see Why AILANG and Vision.
Generated at build time. 71 planned features across 3 upcoming versions.