{"id":46458955,"url":"https://github.com/ai-sdlc-framework/ai-sdlc","last_synced_at":"2026-05-28T23:01:43.555Z","repository":{"id":342434034,"uuid":"1152413600","full_name":"ai-sdlc-framework/ai-sdlc","owner":"ai-sdlc-framework","description":"Declarative governance framework for AI-augmented software development lifecycles","archived":false,"fork":false,"pushed_at":"2026-05-21T22:36:57.000Z","size":11270,"stargazers_count":21,"open_issues_count":4,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-22T02:23:36.774Z","etag":null,"topics":["ai-agents","ai-coding-agents","ai-governance","developer-tools","devops","golang","llm-ops","open-source","orchestration","progressive-autonomy","python","quality-gates","sdlc","typescript"],"latest_commit_sha":null,"homepage":"https://ai-sdlc.io","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ai-sdlc-framework.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":"GOVERNANCE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-07T20:54:12.000Z","updated_at":"2026-05-21T22:36:53.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ai-sdlc-framework/ai-sdlc","commit_stats":null,"previous_names":["ai-sdlc-framework/ai-sdlc"],"tags_count":64,"template":false,"template_full_name":null,"purl":"pkg:github/ai-sdlc-framework/ai-sdlc","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-sdlc-framework%2Fai-sdlc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-sdlc-framework%2Fai-sdlc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-sdlc-framework%2Fai-sdlc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-sdlc-framework%2Fai-sdlc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ai-sdlc-framework","download_url":"https://codeload.github.com/ai-sdlc-framework/ai-sdlc/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai-sdlc-framework%2Fai-sdlc/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33629560,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-28T02:00:06.440Z","response_time":99,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-coding-agents","ai-governance","developer-tools","devops","golang","llm-ops","open-source","orchestration","progressive-autonomy","python","quality-gates","sdlc","typescript"],"created_at":"2026-03-06T03:00:27.430Z","updated_at":"2026-05-28T23:01:43.543Z","avatar_url":"https://github.com/ai-sdlc-framework.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# AI-SDLC Framework\n\n**The Decision Engine for spec-driven AI workflows**\n\n[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![CI](https://github.com/ai-sdlc-framework/ai-sdlc/actions/workflows/ci.yml/badge.svg)](https://github.com/ai-sdlc-framework/ai-sdlc/actions/workflows/ci.yml)\n[![Spec Version](https://img.shields.io/badge/spec-v1alpha1-orange.svg)](#specification--versioning)\n[![Coverage](https://codecov.io/gh/ai-sdlc-framework/ai-sdlc/branch/main/graph/badge.svg)](https://codecov.io/gh/ai-sdlc-framework/ai-sdlc)\n[![Docs](https://img.shields.io/badge/docs-ai--sdlc.io-0a0a0a.svg)](https://ai-sdlc.io/docs)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n\n[Website](https://ai-sdlc.io) · [Documentation](https://ai-sdlc.io/docs) · [Specification](https://ai-sdlc.io/docs/spec/spec) · [Getting Started](https://ai-sdlc.io/docs/getting-started) · [Vision](VISION.md) · [Contributing](CONTRIBUTING.md)\n\n\u003c/div\u003e\n\n---\n\n## What this is\n\nAI-SDLC is the **Decision Engine** for spec-driven AI workflows — the execution-and-governance half of a spec-driven development stack. Operators frontload the load-bearing decisions through a Definition-of-Ready gate; an autonomous orchestrator dispatches developer subagents through the dependency graph; cross-harness reviewers (Claude × Codex × …) verify the work in parallel; DSSE attestations seal every change; pull requests open themselves.\n\nThe leverage move is **cost asymmetry**: operator decisions made upfront — with full context, time to think, and access to stakeholders — are cheap and (mostly) correct. AI decisions made mid-execution under uncertainty are expensive and often wrong. The framework's value is not \"AI writes code\"; it's **\"AI executes well-specified contracts deterministically.\"** Those are different products with different reliability profiles.\n\nThe operator's role shifts to **decision steward** — frame open questions, resolve them, sign off on resolutions, monitor the pipeline. Typing and rubber-stamping go to the framework.\n\nAI-SDLC covers the **contract → shipped** half of the spec-driven funnel. Front-of-funnel tools like [GitHub Spec Kit](https://github.com/github/spec-kit) cover **idea → contract**; the two systems compose at the seam where a spec artifact becomes a backlog task ready for DoR. See [RFC-0036](spec/rfcs/RFC-0036-spec-kit-bridge-adopter-authoring.md) for the bridge design and adopter authoring model.\n\n\u003e **Read first:** [`VISION.md`](VISION.md) is the organizing thesis — the design philosophy that grounds every RFC, every CLI, every gate. If something in this repo doesn't trace back to one of its principles, that's a signal we've drifted.\n\n---\n\n## The problem AI-SDLC solves\n\nAI agents can build small greenfield projects, but software falls apart as it grows. The data is consistent:\n\n- **Productivity paradox** — Experienced developers using AI tools are 19% slower on mature codebases, despite believing they are 20% faster ([METR 2025](https://metr.org))\n- **Quality decline** — Refactoring dropped from 25% to 10% of changes; code churn rose from 5.5% to 7.9% ([GitClear 2024](https://www.gitclear.com))\n- **Stability regression** — Every 25% increase in AI adoption correlates with a 7.2% drop in system stability ([Google DORA 2024](https://dora.dev))\n- **Trust gap** — Only 3% of developers express high trust in AI output ([Stack Overflow 2025](https://survey.stackoverflow.co))\n\nThe root cause is not that AI agents write bad code. It is that **nobody orchestrates how they work as the codebase grows** — every decision gets deferred to the worst possible moment, made by the actor with the least context. AI-SDLC flips that.\n\n---\n\n## The five pillars\n\nThe framework is one cohesive system, but it ships as five pillars you can adopt incrementally.\n\n### 1. The Decision Engine — [RFC-0011](spec/rfcs/RFC-0011-definition-of-ready-gate.md) · [RFC-0035](spec/rfcs/RFC-0035-decision-catalog-operator-routing.md)\n\nA Definition-of-Ready gate (RFC-0011) refuses to dispatch tasks the operator hasn't actually decided yet. A forthcoming Decision Catalog (RFC-0035, Draft) makes the operator's open-question queue a first-class resource — ranked by leverage, routed to the right actor, surfaced with framework recommendations + counter-arguments + sub-decision graphs. The framework recommends; the operator decides; the orchestrator executes. → [Concept page](https://ai-sdlc.io/docs/concepts/dor-gate)\n\n### 2. Autonomous Pipeline Orchestrator — [RFC-0015](spec/rfcs/RFC-0015-autonomous-pipeline-orchestrator.md)\n\n`cli-orchestrator tick` walks the dependency graph (RFC-0014), runs admission filters (blocked, in-flight, DoR, dispatchability), dispatches admitted tasks into isolated git worktrees, runs the Step 0-13 pipeline (dev agent → 3 reviewers → attestation sign → PR open), quarantines failures, and resumes from checkpoint commits on interruption. Operators monitor; they don't type. Feature flag: `AI_SDLC_AUTONOMOUS_ORCHESTRATOR=experimental`. → [Concept page](https://ai-sdlc.io/docs/concepts/autonomous-orchestrator) · [Runbook](docs/operations/orchestrator-runbook.md)\n\n### 3. Cross-Harness Review — [RFC-0010](spec/rfcs/RFC-0010-parallel-execution-worktree-pooling.md) §13\n\nThree reviewer subagents run in parallel on every change. DSSE envelopes carry a `harness` field that identifies the execution harness behind each review, and `verify-attestation` enforces **independence by construction**: if Claude implemented, Claude cannot also be the code or test reviewer. Codex reviews Claude's work and vice versa. Reviewer collusion is mechanically impossible. → [Concept page](https://ai-sdlc.io/docs/concepts/cross-harness-review) · [Runbook](docs/operations/cross-harness-review.md)\n\n### 4. Operator TUI — [RFC-0023](spec/rfcs/RFC-0023-operator-tui-pipeline-monitoring.md)\n\nA live terminal interface with five panes: decisions-pending (RFC-0035), pipeline + PRs, dependency graph, configuration, and analytics. Foregrounds load-bearing decisions and stays out of the way for the rest. → [Concept page](https://ai-sdlc.io/docs/concepts/operator-tui)\n\n### 5. Declarative Governance\n\nDeclarative resources for the whole lifecycle: `Pipeline`, `Decision`, `AgentRole`, `QualityGate`, `AutonomyPolicy`, `AdapterBinding` — all with JSON Schema (draft 2020-12) under [`spec/schemas/`](spec/schemas/). Quality gates run advisory → soft-mandatory → hard-mandatory with cross-harness review and DSSE attestation. Adopters declare a compliance posture ([RFC-0022](spec/rfcs/RFC-0022-compliance-posture-audit-surface.md)) and the framework derives gate defaults — EU AI Act, NIST AI RMF, ISO 42001. → [Specification](spec/spec.md)\n\n---\n\n## Quick start\n\n```bash\n# 1. Install the Claude Code plugin (recommended)\n/plugin marketplace add ai-sdlc-framework/ai-sdlc\n/plugin install ai-sdlc@ai-sdlc\n/reload-plugins\n\n# 2. Scaffold your repository\nai-sdlc init\n\n# 3. Dispatch your first task\n/ai-sdlc execute AISDLC-42\n```\n\nFull setup, runner configuration, agent-runner reference, and the autonomous-orchestrator opt-in are in the documentation:\n\n→ [Getting Started](https://ai-sdlc.io/docs/getting-started) · [Tutorials](https://ai-sdlc.io/docs/tutorials) · [API Reference](https://ai-sdlc.io/docs/api-reference) · [Operations Runbooks](docs/operations/)\n\nThe framework is agent-agnostic — Claude Code, Codex, Cursor, Copilot, Aider, or any OpenAI-compatible API. See the [Agent Runner Reference](https://ai-sdlc.io/docs/api-reference/runners).\n\n---\n\n## For AI agents and human contributors discovering this repo\n\nIf you are an AI agent or a new contributor coming to this codebase for the first time, read these documents in order. Each is canonical for its concern:\n\n1. **[`VISION.md`](VISION.md)** — the organizing thesis (Decision Engine, cost asymmetry, operator-as-decision-steward, anti-patterns ruled out). Every decision in this repo should trace back here.\n2. **[`CLAUDE.md`](CLAUDE.md)** — operating conventions for any agent or contributor working in this repo: git flow (always rebase, never merge), branch + commit conventions, pre-push hooks, attestation requirements, backlog workflow, Pattern-C worktree isolation, plugin MCP routing. **Load this before doing any work.**\n3. **[`CHARTER.md`](CHARTER.md)** — project governance, IP policy, CNCF alignment.\n4. **[`spec/rfcs/README.md`](spec/rfcs/README.md)** — the architectural decisions registry. Every load-bearing design choice lives as an RFC. The registry table is the canonical lookup for numbers and lifecycle states; the Critical Path section traces dependencies.\n5. **[`spec/spec.md`](spec/spec.md)** + **[`spec/`](spec/)** — the normative specification: resource model, policy enforcement, autonomy, agents, adapters, metrics.\n\nCanonical execution paths (when working inside a Claude Code session):\n\n| Use case | Command | Billing |\n|---|---|---|\n| Internal dogfood (backlog tasks) | `/ai-sdlc execute \u003ctask-id\u003e` | Subscription |\n| Manual cleanup | `/ai-sdlc cleanup [\u003ctask-id\u003e]` | n/a |\n| Shell-driven autonomous tick | `cli-orchestrator tick --spawner claude` | Subscription |\n| GitHub issue / unattended / CI | `pnpm --filter @ai-sdlc/dogfood watch --issue \u003cid\u003e` | API key |\n\nRules of thumb to internalize before pushing code:\n\n- **Never merge PRs.** Only humans do. `gh pr merge` is off-limits.\n- **Always rebase** feature branches onto main. Never merge main in.\n- **Pattern C**: the parent working tree is read-only. All code work happens in `.worktrees/\u003ctask-id\u003e/`. `/ai-sdlc execute` sets this up automatically.\n- **Attestation is required** on `main`. Code PRs that touch source must carry a DSSE envelope signed by the reviewer chain. Docs-only PRs bypass.\n- **Cross-repo writes** go through `permittedExternalPaths` in the task frontmatter.\n\nThe plugin's slash commands and MCP tools are documented in [`ai-sdlc-plugin/README.md`](ai-sdlc-plugin/README.md). The Step 0-13 pipeline is in [`pipeline-cli/README.md`](pipeline-cli/README.md).\n\n---\n\n## Packages\n\n| Package | Path | Purpose |\n|---|---|---|\n| `@ai-sdlc/orchestrator` | [`orchestrator/`](orchestrator/) | Orchestrator runtime — CLI, runners, admission, state store |\n| `@ai-sdlc/pipeline-cli` | [`pipeline-cli/`](pipeline-cli/) | Step 0-13 pipeline runtime; `cli-orchestrator`, `cli-deps`, `cli-decisions`, `cli-tui` |\n| `ai-sdlc-plugin` | [`ai-sdlc-plugin/`](ai-sdlc-plugin/) | Claude Code plugin — hooks, slash commands, reviewer subagents, MCP server |\n| `@ai-sdlc/sdk` | [`sdk-typescript/`](sdk-typescript/) | TypeScript SDK |\n| `ai-sdlc-framework` | [`sdk-python/`](sdk-python/) | Python SDK (`pip install ai-sdlc-framework`) |\n| `sdk-go` | [`sdk-go/`](sdk-go/) | Go SDK + Kubernetes-style operator CRDs |\n| `@ai-sdlc/conformance` | [`conformance/`](conformance/) | Language-agnostic conformance test suite |\n| `spec/` | [`spec/`](spec/) | Formal specification, RFCs, JSON schemas |\n\nFor development setup (`pnpm install`, build, test, schema validation), see [`docs/getting-started/`](docs/getting-started/) and [`CONTRIBUTING.md`](CONTRIBUTING.md).\n\n---\n\n## Specification \u0026 versioning\n\nThe specification follows Kubernetes-style API maturity: **`v1alpha1`** today; `v1beta1` follows a 9-month deprecation window; `v1` follows a 12-month window. Resource types, policy enforcement levels, autonomy, agents, and adapters all live under [`spec/`](spec/) with JSON Schema (draft 2020-12) under [`spec/schemas/`](spec/schemas/).\n\nArchitectural changes go through the [RFC process](spec/rfcs/README.md). The registry there is the canonical lookup for every RFC number — active, reserved, withdrawn, and implemented.\n\n---\n\n## Contributing, governance, license\n\n- **Contributing:** [`CONTRIBUTING.md`](CONTRIBUTING.md) — bug reports, feature requests, code, and spec changes (via [RFC](spec/rfcs/README.md))\n- **Governance:** [`GOVERNANCE.md`](GOVERNANCE.md) — project roles, decision making, SIG structure\n- **Charter:** [`CHARTER.md`](CHARTER.md) — mission, scope, IP policy, CNCF alignment\n- **License:** [Apache 2.0](LICENSE) — commercial and open-source use, no restrictions\n- **Code of Conduct:** [Contributor Covenant v2.1](CODE_OF_CONDUCT.md)\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**[Website](https://ai-sdlc.io)** · **[Documentation](https://ai-sdlc.io/docs)** · **[Specification](https://ai-sdlc.io/docs/spec/spec)** · **[Vision](VISION.md)** · **[Pricing](https://ai-sdlc.io/pricing)**\n\nIf you find this project useful, please consider giving it a star.\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai-sdlc-framework%2Fai-sdlc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fai-sdlc-framework%2Fai-sdlc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai-sdlc-framework%2Fai-sdlc/lists"}