Execution Engine (alp run) #
Topologically sorts your dependency graph in < 2ms, compiles precise context bundles, and orchestrates agents through the full lifecycle.
The open standard & high-performance execution engine for AI-driven software engineering. Write a machine-readable spec β let your agents plan, build, verify, and remember.
Git standardized version control. Docker standardized environments. OpenAPI standardized APIs. ALP standardizes how AI builds software.
Today every AI coding assistant (Devin, Claude Code, Cursor, OpenHands) relies on unstructured prompts and brittle context-scraping. They forget decisions, overwrite each other's work, and lose track of dependencies. ALP replaces scattered README.md, PRD.md, AGENTS.md, and TASKS.md files with one deterministic protocol stored natively in your repository (.alp/).
ALP turns your repository into a deterministic, machine-readable project specification that any AI agent can read, understand, and act on.
flowchart LR
ALP[.alp/ Files] --> Parser[ALP Parser]
Parser --> Graph[Dependency Graph]
Graph --> Engine[Execution Engine]
Engine --> Agent[AI Agent]
Agent --> Task[Task Execution]
Task --> Verify[Quality Gates]
Verify --> State[Project State]
.alp/ files using the ALP protocol
Create a .alp file in your repository:
!alp-version: 80.0.0
@project
id: my-project
name: My Project
version: 1.0.0
state: active
@feature
id: feat-auth
name: Authentication
description: OAuth2 + JWT authentication flow
@task
id: task-login-ui
name: Build login UI
status: [ ]
depends_on:
- task-setup-db
verify:
- npm run test:login
- npm run lint:login
@agent
id: agent-frontend
name: Frontend Specialist
capabilities: [react, typescript, tailwind]
Then run:
alp validate
alp run
alp verify task-login-ui
ALP parses your workspace into a Directed Acyclic Graph (DAG). Agents only receive the exact context they need, exactly when they need it.
graph TD
subgraph Repository [Your Repository .alp/]
D[Decision: Use PostgreSQL] --> T1[Task: Setup DB Schema]
T1 --> T2[Task: Build REST API]
R[Rule: No Raw SQL] --> T2
C[Contract: @contract c-api] --> T2
end
subgraph ExecutionEngine [Execution Engine - alp run]
T2 -->|Context Bundle - 1.8ms| Agent[Claude / Cursor Agent]
end
subgraph QualityGates [Quality Gates - alp verify]
Agent -->|npm test| V{Tests Pass?}
V -->|Exit 0| X[Mark x Done]
V -->|Non-Zero| B[Mark ! Blocked]
end
flowchart LR
subgraph SwarmNodes [Autonomous Swarm Nodes]
A1[Agent Alpha\nCoder] <--> EM((Event Mesh\nPub/Sub))
A2[Agent Beta\nReviewer] <--> EM
A3[Agent Gamma\nTester] <--> EM
end
subgraph Marketplace [Swarm Marketplace]
EM <--> SWM[Skill Registry\n@swarm_marketplace]
SWM -->|Discover & Invoke| Cost[Cost & Metering Engine]
end
Terminal CLI interface: run, marketplace, event-mesh, policy, vault, verify.
Parses .alp files and computes Kahn topological sorts over the dependency graph in sub-2ms.
Real-time MCP integration for Claude Desktop, Cursor, and any compliant client.
Language Server with IntelliSense, go-to-definition, and rich hover metadata.
Official TypeScript and Python SDKs with complete 1:1 implementation parity.
Official Go, Rust, and Java SDKs with core parsing, graph, and workspace APIs.
Autonomous skill registry, provider discovery, invocation, and cost tracking (v38.0.0).
The unified ALP desktop IDE (Mac/Windows/Linux). Faster, more secure, and error-free vs. fragmented multi-IDE setups. Native @autonomous-lifecycle-protocol-alp/parser, Monaco editor, agent manager, IDE Intelligence with AI suggestions/predictions/review, and Autonomous Orchestration with self-healing DAGs.
npm install -g @autonomous-lifecycle-protocol-alp/cli
alp init
This creates a .alp/ directory with a starter project.alp file.
Create .alp/features.alp:
!alp-version: 80.0.0
@feature
id: feat-auth
name: User Authentication
description: OAuth2 + JWT authentication flow
@task
id: task-login-ui
name: Build login UI
status: [ ]
depends_on:
- task-setup-db
verify:
- npm run test:login
- npm run lint:login
alp validate
alp run
alp verify task-login-ui
Released versions are tracked in the versioning spec. This section captures active and planned focus areas.
| Era | Versions | Focus |
|---|---|---|
| V8 β The Cognitive Era | 12.0.0β12.x | AI-native planning & reasoning: GoalDecomposer, Planner, Reflector, memory-augmented inference |
| V9 β The Collaborative Era | 13.0.0β13.x | Multi-agent negotiation, contracts-as-protocol, reputation & trust scoring, composable agent teams |
| V10 β The Verifiable Era | 14.0.0β14.x | End-to-end provenance, signed execution traces, zero-knowledge policy proofs, tamper-evident audit ledger |
| V11 β The Ambient Era | 15.0.0β15.x | Fully autonomous long-running swarms, safe self-modifying workflows, edge-native runtime, live upgrade & migration |
| V12 β The Sentinel Era | 16.0.0β16.x | Immutable execution traces, self-healing workflows, predictive governance, swarm resilience, cost optimization |
| V13 β The Universal Era | 17.0.0β17.x | Cross-protocol interoperability (OpenAPI, GraphQL, gRPC, AsyncAPI), universal adapters, bidirectional sync |
V9 β Native Desktop (v80.0.0) β SHAM IDE cross-platform release with native ALP integration, Monaco editor, agent manager, auto-updater, and Pro/Enterprise licensing.
V10 β The Intelligence Era (v80.0.0) β Autonomous multi-agent orchestration with self-healing DAGs, predictive governance, edge-native execution, and AI-native lifecycle management.