{"id":47025969,"url":"https://github.com/humansys/raise","last_synced_at":"2026-04-07T04:03:45.239Z","repository":{"id":343466690,"uuid":"1157484336","full_name":"humansys/raise","owner":"humansys","description":"RaiSE Framework — Reliable AI-assisted Software Engineering. Lean methodology + deterministic toolkit for building production software with AI.","archived":false,"fork":false,"pushed_at":"2026-03-24T06:17:52.000Z","size":26639,"stargazers_count":60,"open_issues_count":3,"forks_count":7,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-03-25T07:56:18.984Z","etag":null,"topics":["ai","cli","developer-tools","lean","methodology","python","software-engineering"],"latest_commit_sha":null,"homepage":"https://raiseframework.ai","language":"Python","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/humansys.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-13T21:49:39.000Z","updated_at":"2026-03-24T19:46:29.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/humansys/raise","commit_stats":null,"previous_names":["humansys/raise"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/humansys/raise","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansys%2Fraise","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansys%2Fraise/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansys%2Fraise/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansys%2Fraise/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/humansys","download_url":"https://codeload.github.com/humansys/raise/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansys%2Fraise/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31499216,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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","cli","developer-tools","lean","methodology","python","software-engineering"],"created_at":"2026-03-11T23:04:28.893Z","updated_at":"2026-04-07T04:03:45.234Z","avatar_url":"https://github.com/humansys.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RaiSE\n\n**Reliable AI Software Engineering** — Ship quality software at AI speed.\n\n\u003e *Raise your craft, feature by feature.*\n\n---\n\n## What is RaiSE?\n\nRaiSE is a methodology + toolkit for professional developers who use AI assistants. It solves the problem of AI-generated code that's fast but inconsistent: governance that works naturally, validation at every step, and memory that persists across sessions.\n\n**The RaiSE Triad:**\n\n```\n        RaiSE Engineer\n        (You - Strategy, Judgment, Ownership)\n              │\n              │ collaborates with\n              ▼\n           Rai\n   (AI Partner - Execution + Memory)\n              │\n              │ governed by\n              ▼\n           RaiSE\n    (Methodology + Toolkit)\n```\n\n**Rai** is your AI collaborator — not a generic assistant, but a partner trained in the discipline of reliable AI software engineering. Rai remembers your patterns, calibrates to your velocity, and maintains coherence across sessions.\n\n---\n\n## Developer Onboarding\n\n### Quick Install\n\n```bash\npipx install rai-cli\nrai --version\n```\n\n\u003e **Detailed instructions** for macOS, Linux, and Windows (WSL) — including known pitfalls and troubleshooting — are in the **[Installation Guide](docs/installation.md)**.\n\n### Onboarding with Rai\n\nOnce installed, open Claude Code in the project directory and run:\n\n```\n/rai-welcome\n```\n\nThis single command will:\n- **Detect your situation** (new developer, returning developer, etc.)\n- **Create your profile** (`~/.rai/developer.yaml`) with your name and pattern prefix\n- **Build the knowledge graph** so Rai has project context\n- **Set up session context** (derived from git automatically)\n- **Optionally customize** communication preferences (language, style)\n- **Verify everything works**\n\nAfter welcome completes, start working:\n\n```\n/rai-session-start\n```\n\nThis loads your context, memory, and proposes focused work.\n\n### What You Get\n\n| Shared (committed) | Personal (gitignored) |\n|--------------------|-----------------------|\n| Patterns (`.raise/rai/memory/patterns.jsonl`) | Session history (`.raise/rai/personal/sessions/`) |\n| Governance docs | Session state (`.raise/rai/personal/session-state.yaml`) |\n| Skills, methodology | Calibration data (`.raise/rai/personal/calibration.jsonl`) |\n| Work artifacts | Knowledge graph (`.raise/rai/memory/index.json`) |\n\nEach developer builds their own personal context through working sessions. Pattern IDs are developer-prefixed (e.g., PAT-A-001 for Alice, PAT-B-001 for Bob) to prevent collisions in shared repositories.\n\n---\n\n## Usage\n\n### Initialize RaiSE on Your Project\n\n```bash\n# Navigate to your existing project\ncd your-project\n\n# Initialize RaiSE governance structure\nrai init --detect\n\n# Open Claude Code and run onboarding\n/rai-welcome\n```\n\nThis scaffolds the `.raise/` directory, detects your project's conventions (language, testing framework, linting), and builds the knowledge graph.\n\n### Daily Workflow\n\nA typical session follows this pattern:\n\n```\n1. /rai-session-start          # Load context, see what's pending\n2. /rai-story-start             # Create branch, define scope\n3. /rai-story-design            # Design the approach (recommended)\n4. /rai-story-plan              # Break into atomic tasks\n5. /rai-story-implement         # TDD execution with validation gates\n6. /rai-story-review            # Retrospective, capture patterns\n7. /rai-story-close             # Merge, cleanup\n8. /rai-session-close           # Persist learnings for next session\n```\n\nYou don't need to complete all steps in one session — Rai remembers where you left off.\n\n### What Rai Remembers\n\n- **Patterns** — Reusable insights learned from your work (e.g., \"always validate config at boundaries\")\n- **Calibration** — Your velocity, strengths, growth edges\n- **Session history** — What you worked on, decisions made, items deferred\n- **Coaching corrections** — Mistakes Rai made and learned from\n\nEach session builds on the last. Over time, Rai becomes a more effective collaborator for your specific codebase and working style.\n\n---\n\n## Available Skills\n\nSkills are structured processes that guide AI-assisted development. Run them as `/skill-name` in Claude Code.\n\n### Session Lifecycle\n| Skill | Purpose |\n|-------|---------|\n| `/rai-welcome` | One-time developer onboarding |\n| `/rai-session-start` | Begin a session with memory and context |\n| `/rai-session-close` | End a session, persist learnings |\n\n### Story Lifecycle\n| Skill | Purpose |\n|-------|---------|\n| `/rai-story-start` | Initialize a story with branch and scope |\n| `/rai-story-design` | Create lean specs for complex stories |\n| `/rai-story-plan` | Decompose into atomic tasks |\n| `/rai-story-implement` | Execute with TDD and validation gates |\n| `/rai-story-review` | Retrospective and learnings |\n| `/rai-story-close` | Merge, cleanup, tracking |\n\n### Epic Lifecycle\n| Skill | Purpose |\n|-------|---------|\n| `/rai-epic-start` | Initialize an epic with branch |\n| `/rai-epic-design` | Design multi-story epics |\n| `/rai-epic-plan` | Sequence stories into plans |\n| `/rai-epic-close` | Epic retrospective and merge |\n\n### Discovery Skills\n| Skill | Purpose |\n|-------|---------|\n| `/rai-discover-start` | Initialize codebase discovery |\n| `/rai-discover-scan` | Extract and describe components |\n| `/rai-discover-validate` | Validate synthesized descriptions with human review |\n| `/rai-discover-document` | Generate architecture docs from discovery data |\n\n### Project Skills\n| Skill | Purpose |\n|-------|---------|\n| `/rai-welcome` | One-time developer onboarding |\n| `/rai-project-create` | Guide greenfield project setup |\n| `/rai-project-onboard` | Guide brownfield project onboarding |\n\n### Analysis \u0026 Quality\n| Skill | Purpose |\n|-------|---------|\n| `/rai-research` | Epistemologically rigorous research |\n| `/rai-debug` | Root cause analysis (5 Whys, Ishikawa) |\n| `/rai-quality-review` | Critical code review with external auditor perspective |\n| `/rai-architecture-review` | Evaluate design proportionality and necessity |\n| `/rai-problem-shape` | Guided problem definition at portfolio level |\n\n### Maintenance\n| Skill | Purpose |\n|-------|---------|\n| `/rai-docs-update` | Sync architecture docs with code |\n| `/rai-framework-sync` | Sync framework files across locations |\n| `/rai-publish` | Structured release workflow with quality gates |\n\n---\n\n## CLI Commands\n\nThe `rai` CLI provides deterministic operations:\n\n```bash\n# Build Rai's knowledge graph from project artifacts\nrai graph build\n\n# Query governance concepts\nrai graph context mod-session\n\n# Query Rai's memory\nrai graph query \"velocity patterns\"\n\n# Validate the memory graph (structural + completeness)\nrai graph validate\n\n# Visualize the memory graph as interactive HTML\nrai graph viz                    # Opens in browser\nrai graph viz --output graph.html  # Custom output path\n\n# List releases and their associated epics\nrai release list\n\n# Start a session (creates profile on first run)\nrai session start --name \"YourName\" --project \"$(pwd)\" --context\n\n# Close a session\nrai session close --state-file /tmp/session-output.yaml --project \"$(pwd)\"\n```\n\n---\n\n## Project Structure\n\nThis is a **uv workspace monorepo** with 5 packages:\n\n| Package | Description | PyPI |\n|---------|-------------|------|\n| **raise-core** | Graph, memory, patterns, discovery engine | `pip install raise-core` |\n| **raise-cli** | `rai` CLI toolkit (session, graph, backlog, gates) | `pip install raise-cli` |\n| **rai-agent** | Autonomous agent daemon (Telegram, cron, Claude Code) | `pip install rai-agent` |\n| **raise-pro** | Enterprise integrations (Jira, Confluence) | Private |\n| **raise-server** | REST API + PostgreSQL backend | Private |\n\n```\nraise-commons/\n├── packages/\n│   ├── raise-core/        # Core library (graph, memory, patterns)\n│   ├── raise-cli/         # CLI toolkit\n│   ├── rai-agent/         # Agent daemon + Dockerfile\n│   ├── raise-pro/         # Enterprise integrations (private)\n│   └── raise-server/      # API server (private)\n│\n├── .claude/skills/        # Claude Code skills (27 skills)\n├── framework/             # Public textbook (concepts, reference)\n├── .raise/                # Framework engine (memory, gates, templates)\n├── governance/            # Architecture docs, guardrails\n├── work/                  # Epics and story artifacts\n└── docker-compose.yml     # Local dev + rai-agent deployment\n```\n\n## Running rai-agent with Docker\n\nThe fastest way to run rai-agent (Telegram bot + daemon):\n\n```bash\ngit clone https://github.com/humansys/raise.git\ncd raise\ncp .env.example .env   # Edit: add your auth + Telegram bot token\ndocker compose up rai-agent\n```\n\nSee `.env.example` for all supported authentication methods:\n- Claude subscription (Pro/Max) via `claude setup-token`\n- Anthropic API key (BYOK, pay-as-you-go)\n- AWS Bedrock, Google Vertex AI, Azure Foundry\n- LLM Proxy / Gateway\n\n---\n\n## Branch Model\n\n```\nmain (stable releases)\n  └── dev (development)\n        └── story/s{N}.{M}/{name}\n```\n\n- Stories branch from and merge to `dev`\n- Epics are logical containers (directory + tracker), not branches\n- `main` receives releases from `dev`\n\n---\n\n## Core Concepts\n\n| Concept | Description |\n|---------|-------------|\n| **RaiSE Engineer** | You — the human who directs AI-assisted development |\n| **Rai** | AI partner with memory, calibration, and accumulated judgment |\n| **Skill** | Structured Claude Code prompt for a methodology phase |\n| **Validation Gate** | Quality checkpoint with specific criteria |\n| **Guardrail** | Constraint that guides AI behavior |\n| **ShuHaRi** | Mastery levels (beginner → practitioner → master) that adapt Rai's verbosity |\n\nSee the full [Glossary](framework/reference/glossary.md) for canonical terminology.\n\n---\n\n## Key Principles\n\nFrom the [Constitution](framework/reference/constitution.md):\n\n1. **Humans Define, Machines Execute** — Specs are source of truth\n2. **Governance as Code** — Standards versioned in Git\n3. **Validation Gates** — Quality checked at each phase\n4. **Observable Workflow** — Every decision traceable\n5. **Jidoka** — Stop on defects, don't accumulate errors\n\n---\n\n## Status\n\nCurrent stable release: `v2.3.0`. Next release: `v2.4.0` (in development). The framework is being used in production.\n\nWe value your feedback:\n\n- **Questions?** Open an [issue](https://gitlab.com/humansys-demos/product/raise1/raise-commons/-/issues)\n- **Found a bug?** Open an [issue](https://gitlab.com/humansys-demos/product/raise1/raise-commons/-/issues) with reproduction steps\n- **Ideas?** We want to hear them — open an issue or reach out directly\n\n---\n\n## License\n\n[Apache-2.0](LICENSE)\n\n---\n\n*RaiSE — Reliable AI Software Engineering*\n*Neither is complete alone.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumansys%2Fraise","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhumansys%2Fraise","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumansys%2Fraise/lists"}