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 v0.7.0
- AILANG: Auto-Caps and Capability Inference
- Module Import Resolution Bug
- M-REPL1: REPL Persistent Type Bindings & Module Loading
- M-TOOLING: Deterministic CLI for AI Agents (v0.3.15)
- M-UX2: Dev Experience Polish
- M-CALL-SUGAR: Optional Parenthesized Call Syntax
- M-REFLECT: Structural Reflection & User-Defined Type Classes
Planned for v0.6.1
- M-AGENT-PROTOCOL: Agent-to-Agent Communication Protocol
- M-EVAL-AGENT-QUEUE: Queue-Based Agent Evaluation Architecture
- M-EVAL-AGENT: Multi-Agent Eval Benchmark Suite
- DX-17 Phase 2: Normalize TList to TApp at Parse Time
- Evaluation Dashboard Reliability
- AILANG Execution Profiles — A Unified Architecture for Games, Agents, Services, and Tools
- Global Collaboration Hub - Cross-Computer Agent Collaboration
- M-CODEGEN-V3: Binding Hoisting for VALUE-Position Lets
- M-CODEGEN-VALUE-TYPES: Size-Based Pointer vs Value Strategy
- M-DX: Add Directory Support to
ailang check - M-DX11 Phase 2: Type Checker Debug Event Emission
- M-DX11 Phase 2 Sprint Plan: Debug Event Emission
- M-ENV-TYPE: Fix std/env EnvError Type Parameter Bug
- M-EXEC-GEMINI Sprint Plan: Gemini CLI Executor Implementation
- M-EXEC: Multi-Executor Support for AI Coding Agents
- M-GEMINI-INTERACTIONS: Google Gemini Interactions API Support
- M-LETREC-SCOPING: Fix Letrec Recursive Binding Scope Regression
- Sprint Plan: M-OPENAI-RESPONSES-API
- M-OPENAI-RESPONSES-API: OpenAI Responses API & Agent Module
- M-VERIFY: ARC-Style Verification & Policy Mode
- Semantic Caching: Future Work (v0.6.0+)
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. 28 planned features across 2 upcoming versions.