{"id":48174202,"url":"https://github.com/ido4-dev/ido4","last_synced_at":"2026-04-04T17:36:25.942Z","repository":{"id":344655506,"uuid":"1175357314","full_name":"ido4-dev/ido4","owner":"ido4-dev","description":"Development Governance Platform — deterministic methodology enforcement for AI-augmented teams","archived":false,"fork":false,"pushed_at":"2026-04-01T11:40:31.000Z","size":2738,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-01T13:30:16.820Z","etag":null,"topics":["ai-agents","audit-trail","business-rules","claude-code","compliance","developer-tools","governance","mcp","mcp-server","multi-agent","typescript","wave-methodology"],"latest_commit_sha":null,"homepage":"https://ido4.dev","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ido4-dev.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"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":"2026-03-07T15:49:46.000Z","updated_at":"2026-04-01T11:40:35.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ido4-dev/ido4","commit_stats":null,"previous_names":["ido4-dev/ido4"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/ido4-dev/ido4","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ido4-dev%2Fido4","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ido4-dev%2Fido4/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ido4-dev%2Fido4/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ido4-dev%2Fido4/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ido4-dev","download_url":"https://codeload.github.com/ido4-dev/ido4/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ido4-dev%2Fido4/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31407645,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T10:20:44.708Z","status":"ssl_error","status_checked_at":"2026-04-04T10:20:06.846Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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","audit-trail","business-rules","claude-code","compliance","developer-tools","governance","mcp","mcp-server","multi-agent","typescript","wave-methodology"],"created_at":"2026-04-04T17:36:25.837Z","updated_at":"2026-04-04T17:36:25.931Z","avatar_url":"https://github.com/ido4-dev.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ch1 align=\"center\"\u003eido4\u003c/h1\u003e\n  \u003cp align=\"center\"\u003e\u003cstrong\u003eAI-Hybrid Software Development at Scale\u003c/strong\u003e\u003c/p\u003e\n  \u003cp align=\"center\"\u003eThe platform that gives AI agents shared understanding, institutional memory, and quality enforcement\u003c/p\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#see-it-in-action\"\u003eSee It In Action\u003c/a\u003e \u0026middot;\n  \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e \u0026middot;\n  \u003ca href=\"#features\"\u003eFeatures\u003c/a\u003e \u0026middot;\n  \u003ca href=\"https://docs.ido4.dev\"\u003eDocumentation\u003c/a\u003e \u0026middot;\n  \u003ca href=\"#architecture\"\u003eArchitecture\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/MCP-compatible-7C3AED\" alt=\"MCP Compatible\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/tools-58-2563EB\" alt=\"58 MCP Tools\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/tests-1731-16A34A\" alt=\"1731 Tests\"\u003e\n  \u003cimg src=\"https://img.shields.io/npm/l/@ido4/core\" alt=\"MIT License\"\u003e\n\u003c/p\u003e\n\n---\n\nAI agents can write code. But can they understand the full project? Know what was built before them? Pick the highest-leverage task? Build on decisions from previous sessions? Coordinate with other agents without conflicts?\n\n**ido4** is the platform that makes AI-hybrid software development actually work. It runs inside Claude Code (and any MCP-compatible AI environment), giving every AI session full project context — what to build, what's already built, who depends on your output — with deterministic governance ensuring quality at every step.\n\nThe system carries the knowledge, not the agent. Every session starts with accumulated project understanding. Every action is validated through **34 real validation steps** — not LLM instructions that can be hallucinated. Every outcome is recorded so the next session is smarter than the last.\n\n```\n\u003e What should I work on?\n\nget_next_task { agentId: \"agent-alpha\" }\n  Recommended: #42 Auth token rotation (score: 72)\n  cascade:15 | momentum:25 | capability:20 | freshness:12\n  Unblocks 3 downstream tasks. Epic is 60% complete — finish it.\n\n\u003e Load the full context\n\nget_task_execution_data { issueNumber: 42 }\n  ✓ Task spec + acceptance criteria loaded\n  ✓ Upstream: #38 built JWT refresh endpoint (RSA-256, 30min TTL)\n  ✓ Upstream: #41 created user schema with bcrypt hashing\n  ✓ Siblings: #39, #40 established error handling pattern\n  ✓ Downstream: #45, #47, #51 waiting on this task\n  Risk: critical path — 3 of 5 remaining epic tasks depend on #42\n\n\u003e Start the task\n\nstart_task { issueNumber: 42 }\n  ✓ BRE Validation: 6/6 steps passed\n  Task #42 → In Progress. Lock acquired.\n```\n\nThe agent didn't start from scratch. It knew what to work on, why it matters, what was built upstream, and who depends on its output. That's ido4.\n\n## The Problem\n\nAI coding agents can execute. But AI-hybrid development at scale needs more than execution:\n\n- **No shared understanding.** Every AI session starts from scratch. No knowledge of what was built yesterday, what decisions were made, what patterns were established. Context is lost between sessions.\n- **No task intelligence.** Agents pick whatever task seems obvious, not the one that unblocks the most downstream work. No scoring, no cascade analysis, no epic momentum.\n- **No institutional memory.** When Agent A builds an auth service and Agent B needs to consume it next week, there's no structured knowledge transfer. B searches the codebase blind.\n- **No quality enforcement.** Dependencies get violated. Epics ship incomplete. Quality gates get skipped. Nobody can trace what happened when something breaks.\n- **No coordination.** Multiple agents on the same codebase with no awareness of each other — duplicate work, conflicting changes, cascade failures.\n\nTraditional project management tools (Linear, Jira, Notion) track work after the fact. They don't **empower agents** to build effectively. ido4 is the platform that makes AI-hybrid development work — from context delivery through quality enforcement.\n\n## See It In Action\n\nThe sandbox creates a real GitHub project from a [demo codebase](https://github.com/ido4-dev/ido4-demo), embeds governance violations, and discovers them live — using the same tools that govern real projects:\n\n```\n\u003e /ido4dev:onboard\n\nDemo project cloned. Creating governed sandbox...\n✓ Tasks ingested via pipeline, violations embedded, agents registered\n\n══════════════════════════════════════════════\n  LIVE GOVERNANCE ANALYSIS\n══════════════════════════════════════════════\n\nCASCADE BLOCKER: Delivery Engine Core blocking 11 downstream tasks\n  Working in src/notifications/delivery-engine.ts.\n  Channel providers, template renderer, and API endpoint all waiting.\n\nFALSE STATUS: Delivery Status Tracking shows \"In Review\" — no PR\n  Status updated during sync meeting. Implementation not started.\n\nREVIEW BOTTLENECK: Retry Policy PR open 3 days, 0 reviews\n  Changes in src/notifications/retry-policy.ts. Code ready, idle.\n\nINTEGRITY VIOLATION: Idempotency Guard in wrong wave\n  Part of Notification Core capability but assigned to wave-003\n  instead of wave-002. Delivery pipeline can't ship atomically.\n\n══════════════════════════════════════════════\n  INTELLIGENT WORK DISTRIBUTION\n══════════════════════════════════════════════\n\nagent-alpha (notification core — locked on Delivery Engine):\n  → Email Provider       score:47  cascade:15 epic:12 cap:10 fresh:10\n  → Webhook Provider     score:35  cascade:8  epic:12 cap:10 fresh:5\n\nagent-beta (channel providers — available):\n  → Email Provider       score:44  cascade:15 epic:12 cap:7  fresh:10\n  → SMS Provider         score:30  cascade:8  epic:12 cap:7  fresh:3\n\nEvery score is deterministic — computed from dependency graphs,\ncapability completion ratios, agent capabilities, and audit timestamps.\n```\n\nThe sandbox works identically for all three methodologies — Hydro (waves/epics), Scrum (sprints), and Shape Up (cycles/bets). The governance adapts to your methodology; the engine stays the same. [Try the sandbox demo →](https://docs.ido4.dev/getting-started/sandbox/)\n\n## Quick Start\n\n### As a Claude Code Plugin (Recommended)\n\n```bash\n# Set your GitHub token\nexport GITHUB_TOKEN=$(gh auth token)\n\n# Install from the marketplace (no clone, no build)\n/plugin marketplace add ido4-dev/ido4-plugins\n/plugin install ido4dev@ido4-plugins\n\n# Try the interactive sandbox demo\n\u003e /ido4dev:onboard\n```\n\n### As a Standalone MCP Server\n\n```bash\nnpm install @ido4/mcp\n```\n\nAdd to your MCP client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"ido4\": {\n      \"command\": \"npx\",\n      \"args\": [\"@ido4/mcp\"],\n      \"env\": {\n        \"GITHUB_TOKEN\": \"your-token\"\n      }\n    }\n  }\n}\n```\n\n### Initialize a Project\n\n```bash\n# Inside Claude Code with the plugin loaded:\n\u003e Initialize ido4 governance for my-org/my-project\n# The AI calls init_project, creates the GitHub Project V2,\n# sets up custom fields, and writes .ido4/ config\n```\n\n## Features\n\n### Context Assembly \u0026 Task Intelligence\n\nEvery AI session starts with full project understanding — not a blank slate:\n\n- **`get_task_execution_data`** — One call assembles: task spec, upstream dependency context (what was actually built, not just \"done\"), sibling patterns, downstream consumers, epic progress, and quantified risk flags.\n- **`get_next_task`** — 4-dimension scoring recommends the highest-leverage task: cascade value (what unblocks the most), epic momentum (finish what's started), capability match, dependency freshness.\n- **`get_standup_data`** — Full project briefing: blocked tasks, compliance score, recent audit events, agent status, analytics — everything a session needs to orient.\n- **Structured context comments** — Agents write what they built; next agent reads accumulated knowledge. Institutional memory that compounds across sessions.\n\n### The Read-Execute-Write Loop\n\nThis is how institutional memory grows even though individual agents are stateless:\n\n```\nAgent reads context    →  upstream #38 built /auth/refresh (RSA-256, 30min TTL)\n                          upstream #41 created user schema (bcrypt, 3 tables)\n                          sibling #39 established error handling pattern\n\nAgent executes work    →  builds /auth/rotate with sliding window + circuit breaker\n\nAgent writes context   →  \"Created POST /auth/rotate. Used sliding window\n                           (not fixed TTL) for active sessions. Circuit breaker\n                           shared with refresh — single failure domain.\"\n\nNext agent reads       →  gets ALL accumulated context automatically\n```\n\nEvery completed task enriches the system. The 10th agent working on a project has access to everything the first 9 built, decided, and documented — without any of them being \"specialized\" or persistent.\n\n### Deterministic Business Rule Engine\n\nEvery task transition runs through a composable validation pipeline — 34 built-in steps across 5 categories, configurable per methodology:\n\n| Category | What It Validates |\n|---|---|\n| **Workflow** | Status transitions, state machine paths, required fields |\n| **Dependencies** | Completion checks, circular detection, cascade analysis |\n| **Governance** | Container assignment, integrity rules, singularity constraints |\n| **Quality Gates** | PR reviews, test coverage, security scans, task locks |\n| **Risk** | AI suitability assessment, risk level enforcement |\n\nThe BRE is **configurable** — methodology profiles define which steps run for which transitions:\n\n```json\n{\n  \"transitions\": {\n    \"start\": {\n      \"steps\": [\"StatusTransition\", \"Dependency\", \"ContainerAssignment\", \"ContainerIntegrity\"]\n    },\n    \"approve\": {\n      \"steps\": [\"StatusTransition\", \"PRReview:minApprovals=2\", \"SecurityScan\", \"TestCoverage:threshold=80\"]\n    }\n  }\n}\n```\n\n### Multi-Agent Coordination\n\nBuilt for teams deploying multiple AI agents on the same codebase:\n\n- **Task locking** — Agents acquire exclusive locks. No duplicate effort.\n- **Work distribution** — 4-dimension scoring (cascade value, epic momentum, capability match, dependency freshness) recommends the highest-leverage task for each agent.\n- **Coordination state** — Every agent sees who's working on what, recent events, and handoff opportunities.\n- **Complete-and-handoff** — Atomic operation: approve work, release lock, identify unblocked tasks, recommend next work.\n\n### Audit Trail \u0026 Compliance\n\nEvery governance action creates an immutable audit entry:\n\n- **Event-sourced** — Append-only JSONL with in-memory ring buffer for fast queries\n- **Compliance scoring** — Deterministic 0-100 score across 5 weighted categories: BRE pass rate (40%), quality gates (20%), process adherence (20%), container integrity (10%), flow efficiency (10%)\n- **Real analytics** — Cycle time, lead time, throughput, blocking time — computed from actual events, not estimates\n- **Queryable** — Filter by time range, actor, transition type, issue number, session\n\n### Decomposition Pipeline\n\nThe two-artifact pipeline bridges stakeholder understanding and implementation:\n\n```\nido4shape (conversation) → strategic spec → ido4 MCP (codebase analysis) → technical spec → GitHub issues\n      The WHAT                                    The HOW\n```\n\n- **ido4shape** captures multi-stakeholder requirements through conversation — produces a strategic spec with capabilities, success conditions, and functional dependencies\n- **ido4 MCP** decomposes the strategic spec against the actual codebase — a code analysis agent explores the repo, then a technical spec writer produces implementation tasks with effort, risk, AI suitability, and code-level dependencies\n- The **ingestion pipeline** creates GitHub issues: capabilities become epics/bets, tasks become sub-issues — every task traceable to a strategic requirement\n\n### 21 Intelligence Skills\n\nSkills are intelligent workflows that compose multiple tools into project intelligence. Core skills work across all methodologies; methodology-specific variants speak your methodology's language:\n\n| Skill | What It Does |\n|---|---|\n| `/ido4dev:onboard` | Zero-friction onboarding — auto-clones demo, creates sandbox, guided governance discovery |\n| `/ido4dev:guided-demo` | Four-act governance walkthrough — project, discovery, enforcement, pipeline |\n| `/ido4dev:sandbox-explore` | Interactive exploration — 13 structured paths across governance capabilities |\n| `/ido4dev:standup` | Morning briefing — risks, leverage points, highest-impact action |\n| `/ido4dev:board` | Flow intelligence — blockers, cascade risks, false statuses, capability cohesion |\n| `/ido4dev:compliance` | Three-part assessment: quantitative score + structural audit + synthesis |\n| `/ido4dev:health` | 5-second governance verdict: RED / YELLOW / GREEN |\n| `/ido4dev:plan-wave` | Principle-aware wave composition. Also: `/plan-sprint` (Scrum), `/plan-cycle` (Shape Up) |\n| `/ido4dev:retro-wave` | Data-backed retrospective. Also: `/retro-sprint` (Scrum), `/retro-cycle` (Shape Up) |\n| `/ido4dev:decompose` | Decompose a strategic spec into a technical spec via codebase analysis |\n| `/ido4dev:sandbox` | Sandbox lifecycle — create, reset, destroy |\n| `/ido4dev:pilot-test` | End-to-end verification of the entire governance stack |\n\n### CI/CD Quality Gate\n\nA 6-check merge readiness gate that catches what CI alone can't:\n\n1. **Workflow Compliance** — Did the task follow the full governance workflow?\n2. **PR Review** — Does the PR have the required number of approving reviews?\n3. **Dependency Completion** — Are all upstream dependencies satisfied?\n4. **Container Integrity** — Is the grouping container cohesive within its execution container?\n5. **Security Gates** — Are there vulnerability alerts?\n6. **Compliance Threshold** — Does the project meet its compliance score minimum?\n\nEmergency overrides are available — but they're audited and impact the compliance score. Governance doesn't prevent action; it ensures accountability.\n\n## Governance Principles\n\nEach methodology defines its own principles — deterministic rules enforced by the BRE that cannot be bypassed:\n\n| Methodology | Key Principles |\n|---|---|\n| **Hydro** | Epic Integrity (all tasks in an epic must be in the same wave), Active Wave Singularity, Dependency Coherence, Self-Contained Execution, Atomic Completion |\n| **Scrum** | Sprint Singularity, Dependency Coherence, Atomic Sprint Completion. Epics span sprints (no epic-sprint integrity). Type-scoped pipelines enforce different quality gates per work item type. |\n| **Shape Up** | Cycle Singularity, Bet-Cycle Integrity, Circuit Breaker (unfinished at cycle end = killed), Fixed Appetite (time fixed, scope variable) |\n\nPrinciples aren't suggestions — they're compiled into the BRE pipeline. An agent can't start a task that violates dependency coherence. A wave can't close with incomplete tasks. A bet that exceeds its cycle gets killed. The profile defines it. The engine enforces it.\n\n## Architecture\n\n```\n┌──────────────────────────────────────────────────────────────┐\n│  Claude Code Plugin (ido4dev — separate repo)                 │\n│  21 Skills · 4 Agents · 2 Governance Hooks                   │\n├──────────────────────────────────────────────────────────────┤\n│  MCP Server (@ido4/mcp)                                      │\n│  58 Tools · 9 Resources · 8 Prompts · STDIO Transport        │\n├──────────────────────────────────────────────────────────────┤\n│  Core Domain Layer (@ido4/core)                               │\n│                                                               │\n│  ┌──────────┐ ┌──────────┐ ┌────────────┐ ┌──────────────┐  │\n│  │ Tasks    │ │Containers│ │ Agents     │ │ Compliance   │  │\n│  │ BRE (34  │ │Integrity │ │ Work       │ │ Analytics    │  │\n│  │  steps)  │ │ Deps     │ │ Distrib.   │ │ Audit Trail  │  │\n│  └──────────┘ └──────────┘ │ Merge Gate │ └──────────────┘  │\n│                             └────────────┘                    │\n│  ┌──────────────────────────────────────────────────────────┐│\n│  │ Infrastructure: GraphQL (retry · pagination · rate       ││\n│  │ limiting) · GitHub Repositories · Config · Sandbox       ││\n│  └──────────────────────────────────────────────────────────┘│\n├──────────────────────────────────────────────────────────────┤\n│  GitHub Projects V2 · Issues · Pull Requests                  │\n└──────────────────────────────────────────────────────────────┘\n```\n\n### Monorepo Structure\n\n| Package | npm | Description |\n|---|---|---|\n| [`@ido4/core`](packages/core/) | `npm i @ido4/core` | Domain logic — BRE (34 steps), profile-driven services, repositories. Zero CLI dependencies. |\n| [`@ido4/mcp`](packages/mcp/) | `npm i @ido4/mcp` | MCP server — STDIO transport, 58 tools (Hydro), 9 resources, 8 prompts. |\n| [`ido4dev`](https://github.com/ido4-dev/ido4dev) | — | Claude Code plugin — 21 skills, 4 agents, governance hooks. Distributed via [marketplace](https://github.com/ido4-dev/ido4-plugins). |\n\n### 58 MCP Tools (Hydro)\n\nTool counts vary by methodology — Hydro: 58, Scrum: 56, Shape Up: 54 — because container and transition tools are generated dynamically from the methodology profile.\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eTask Governance (18 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`start_task` · `review_task` · `approve_task` · `block_task` · `unblock_task` · `return_task` · `refine_task` · `ready_task` · `get_task` · `get_task_field` · `list_tasks` · `create_task` · `validate_transition` · `validate_all_transitions` · `find_task_pr` · `get_pr_reviews` · `add_task_comment` · `get_sub_issues`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eWave \u0026 Epic Management (9 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`list_waves` · `get_wave_status` · `create_wave` · `assign_task_to_wave` · `validate_wave_completion` · `search_epics` · `get_epic_tasks` · `get_epic_timeline` · `validate_epic_integrity`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eMulti-Agent Coordination (7 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`register_agent` · `list_agents` · `lock_task` · `release_task` · `get_next_task` · `complete_and_handoff` · `get_coordination_state`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eAudit, Analytics \u0026 Compliance (5 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`query_audit_trail` · `get_audit_summary` · `get_analytics` · `get_task_cycle_time` · `compute_compliance_score`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eQuality Gate \u0026 Dependencies (3 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`check_merge_readiness` · `analyze_dependencies` · `validate_dependencies`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eProject \u0026 Sandbox (5 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`init_project` · `get_project_status` · `create_sandbox` · `destroy_sandbox` · `reset_sandbox`\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eComposite Intelligence (4 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n`get_standup_data` · `get_board_data` · `get_compliance_data` · `get_health_data`\n\u003c/details\u003e\n\n## For Enterprise\n\nido4 provides the infrastructure that enterprise AI-hybrid development requires:\n\n**Context at scale.** Every AI session starts with full project understanding — accumulated knowledge from every prior session, dependency context, risk signals, and institutional memory. No agent starts from scratch.\n\n**Compliance documentation.** Every decision is auditable. Every rule enforcement is traceable. The audit trail provides the evidence that enterprise clients demand — who did what, when, and whether the rules were followed.\n\n**Multi-methodology support.** Three built-in profiles: Hydro (wave-based), Scrum (sprint-based), Shape Up (cycle-based). The engine is methodology-agnostic — profiles define states, transitions, containers, integrity rules, and pipelines. Adopt ido4 with your existing methodology while getting deterministic enforcement.\n\n**Quality gates.** Configure minimum PR reviews, test coverage thresholds, and security scan requirements per transition. Gates are enforced deterministically — not as suggestions.\n\n**Multi-agent coordination at scale.** Deploy multiple AI agents on the same codebase with confidence. Each agent has a unique identity, capability profile, and audit trail. Task intelligence recommends the highest-leverage work. Task locking prevents duplicate effort. Handoff chains keep work flowing continuously.\n\n## The New Way of Working\n\nido4 enables a new operating model for software delivery — AI-hybrid development at enterprise scale:\n\n**2 senior humans + AI agents + ido4 = the output of a 10-person team.**\n\n| Role | Provides |\n|---|---|\n| **PM** | Product vision, stakeholder management, strategic decisions |\n| **Tech Architect** | System design, code quality oversight, technical judgment |\n| **AI Agents** | Execution capacity — coding, testing, documentation |\n| **ido4** | **The platform** — context intelligence, institutional memory, task distribution, and deterministic quality enforcement |\n\nThis isn't a better project management tool. It's the infrastructure that makes AI-hybrid software development actually work — where AI agents understand the full project, build on each other's work, and deliver with the quality and coherence that enterprise clients demand.\n\n## Contributing\n\nWe welcome contributions. See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, architecture guide, and testing conventions.\n\n```bash\n# Development\nnpm install\nnpm run build\nnpm run test          # 1,731 tests\n\n# Run with plugin (local development)\nclaude --plugin-dir ../ido4dev\n```\n\n## License\n\n[MIT](LICENSE)\n\n---\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eido4\u003c/strong\u003e — The platform that makes AI-hybrid software development work. At scale. For real.\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fido4-dev%2Fido4","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fido4-dev%2Fido4","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fido4-dev%2Fido4/lists"}