AI-SDLC is an open-source framework designed to orchestrate autonomous software development by structuring the process as a series of explicit, well-defined decisions. It addresses the challenges that arise when AI coding agents are used in software development without structured oversight, such as reduced code quality, increased code churn, and declining trust in AI-generated code. The framework introduces a decision engine that enables users to frontload planning and requirements through a Definition-of-Ready (DoR) gate, ensuring that work items are clearly specified before execution begins. Once a work item is ready, the autonomous orchestrator dispatches developer subagents—such as AI coding agents like Claude Code, Codex, or Cursor—each operating in isolated worktrees and under declared constraints. The orchestrator manages the full workflow, from capturing ideas (issues, RFCs, or emergent findings) to opening pull requests, with human operators involved only for decisions requiring judgment. Cross-harness review is enforced by running three reviewer subagents in parallel, ensuring that the implementer cannot review their own code, and that independence is maintained across different agent harnesses. The framework also integrates DSSE (Digital Signature Standard for Envelopes) attestations, providing signed provenance and content hashes for code changes. AI-SDLC allows users to declare their desired software development lifecycle state and decision policies using YAML, with all resources validated against JSON Schema (draft 2020-12). Declarative resources include Pipelines (defining workflow stages, triggers, and quality gates), Decisions (open questions routed to the appropriate actor or framework), AgentRoles (specifying agent identities, tools, and constraints), QualityGates (policy rules with graduated enforcement), AutonomyPolicies (permissions and oversight thresholds), and AdapterBindings (tool integrations, such as with issue trackers like Linear). The framework is built around five core pillars: autonomous orchestration, cross-harness review, a decision engine, an operator terminal user interface (TUI), and declarative governance. Its design principles draw from established open-source projects including Kubernetes, Terraform, and OpenTelemetry. AI-SDLC is released under the Apache 2.0 license, and its resources and documentation are available for those seeking to structure and automate software development with AI agents while maintaining quality and trust.
AI-SDLC is a Frameworks & SDKs product. It focuses on coordinating and automating the end-to-end software development lifecycle using autonomous AI agents. It is built as an open-source project for software engineering teams. AI-SDLC is open source under the Apache-2.0 license. The product ships for the command line and API, and it can be self-hosted.
It is developed by ai-sdlc-framework, and the product first shipped in 2026. Development happens publicly on GitHub with 53 stars and 1k commits in the last 90 days. PulseGate's similarity index finds few close equivalents — AI-SDLC occupies a relatively distinct niche. Key capabilities include agent orchestration, declarative governance, and cross-harness review.
Latest indexed changes and source events
ai-sdlc-framework/ai-sdlc discovered by the PulseGate indexer
Other apps tracked under the same category.
