{"id":48790748,"url":"https://github.com/divyamohan1993/claude-kanban","last_synced_at":"2026-04-13T19:43:56.687Z","repository":{"id":342744946,"uuid":"1174999575","full_name":"divyamohan1993/claude-kanban","owner":"divyamohan1993","description":"Drop an idea. Walk away. Come back to committed code. Autonomous AI pipeline using Claude Code.","archived":false,"fork":false,"pushed_at":"2026-04-11T23:12:25.000Z","size":958,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-13T19:43:55.380Z","etag":null,"topics":["ai-automation","anthropic","autonomous-agents","ci-cd","claude","claude-code","code-review","developer-tools","express","kanban","nodejs","orchestrator","pipeline","self-healing","sqlite"],"latest_commit_sha":null,"homepage":"https://github.com/divyamohan1993/claude-kanban#readme","language":"JavaScript","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/divyamohan1993.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"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":"2026-03-07T04:58:35.000Z","updated_at":"2026-03-21T12:07:25.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/divyamohan1993/claude-kanban","commit_stats":null,"previous_names":["divyamohan1993/claude-kanban"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/divyamohan1993/claude-kanban","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divyamohan1993%2Fclaude-kanban","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divyamohan1993%2Fclaude-kanban/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divyamohan1993%2Fclaude-kanban/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divyamohan1993%2Fclaude-kanban/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/divyamohan1993","download_url":"https://codeload.github.com/divyamohan1993/claude-kanban/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divyamohan1993%2Fclaude-kanban/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31768649,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T15:25:13.801Z","status":"ssl_error","status_checked_at":"2026-04-13T15:25:09.162Z","response_time":93,"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-automation","anthropic","autonomous-agents","ci-cd","claude","claude-code","code-review","developer-tools","express","kanban","nodejs","orchestrator","pipeline","self-healing","sqlite"],"created_at":"2026-04-13T19:43:55.760Z","updated_at":"2026-04-13T19:43:56.645Z","avatar_url":"https://github.com/divyamohan1993.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# ◆ Claude Kanban\n\n### Autonomous AI Build Pipeline\n\n**Drop an idea. Walk away. Come back to committed code.**\n\n[![CI](https://github.com/divyamohan1993/claude-kanban/actions/workflows/ci.yml/badge.svg)](https://github.com/divyamohan1993/claude-kanban/actions/workflows/ci.yml)\n[![CodeQL](https://github.com/divyamohan1993/claude-kanban/actions/workflows/codeql.yml/badge.svg)](https://github.com/divyamohan1993/claude-kanban/actions/workflows/codeql.yml)\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![Tests](https://img.shields.io/badge/tests-305%20passing-brightgreen)]()\n[![Node](https://img.shields.io/badge/node-%E2%89%A518-339933?logo=node.js\u0026logoColor=white)]()\n[![Dependencies](https://img.shields.io/badge/dependencies-5-orange)]()\n[![Platform](https://img.shields.io/badge/platform-Linux%20%7C%20macOS%20%7C%20Windows-lightgrey)]()\n\n\u003cbr\u003e\n\n```mermaid\nflowchart LR\n    A[Idea] --\u003e B[Brainstorm] --\u003e C[Build] --\u003e D{AI Review\\n1-10}\n    D -- \"Score ≥ 8\" --\u003e E[Auto-commit\\n+ push]\n    D -- \"Score 5-7\" --\u003e F[Auto-fix ×3\\nthen re-review]\n    D -- \"Score \u003c 5\" --\u003e G[Human review]\n    F --\u003e D\n    C -. \"errors\" .-\u003e H[Self-healing\\nauto-fix or escalate]\n    H .-\u003e C\n```\n\n\u003c/div\u003e\n\n---\n\nClaude Kanban orchestrates autonomous [Claude Code](https://docs.anthropic.com/en/docs/claude-code) sessions as a zero-touch build-review-ship pipeline. You describe what you want; AI brainstorms, builds, reviews, fixes, and commits. You only step in when it can't fix itself.\n\n5 dependencies. Zero build step. One command to start.\n\n\u003cbr\u003e\n\n## ◆ Quick Start\n\n\u003e **Prerequisite:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code) installed and authenticated.\n\n```bash\n# macOS / Linux\nscripts/start.sh\n\n# Windows\nscripts\\start.bat\n\n# Or manual\npnpm install \u0026\u0026 pnpm start\n```\n\nOpen `http://localhost:51777`. Stop with `scripts/stop.sh` or `scripts\\stop.bat`.\n\n\u003cbr\u003e\n\n## ◆ Two Modes\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n### ◇ Single-Project (Autonomous)\n\nDrop an `idea.md` in a folder. Walk away.\n\n```\nKANBAN_MODE=single-project\nSINGLE_PROJECT_PATH=/path/to/project\nAUTO_PROMOTE_BRAINSTORM=true\n```\n\nDiscovery reads `idea.md` as the north star. Every 30 minutes it analyzes the codebase and creates improvement cards. Each card flows through brainstorm, spec, build, review, auto-fix, commit, push. No human needed.\n\n```\n/your/project/\n  idea.md           ← your vision\n  package.json      ← created by orchestrator\n  src/              ← built autonomously\n```\n\n**Demo included:** `sudo bash autoconfig.sh` → option 1. Watch the orchestrator build an entire project from a single idea file.\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n### ◇ Global (Multi-Project)\n\nTraditional kanban. You create cards, assign project folders, control every stage.\n\n```\nKANBAN_MODE=global\nPROJECTS_ROOT=~/Projects\n```\n\n```\n~/Projects/\n  my-app/\n  another-project/\n```\n\nEvery stage requires manual approval: spec review, build start, code review, commit.\n\n**Human authority in both modes:** Log in anytime. Revert files, reject cards (with reasons the AI learns from), stop builds, pause the pipeline. You always override the orchestrator.\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr\u003e\n\n## ◆ What It Does\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd\u003e\n\n#### ◇ Autonomous Pipeline\nCreate a card, pick a project folder, and the full cycle runs: brainstorm spec, snapshot files, build, AI review (1-10), auto-fix if needed, commit on approve, rollback on reject. Card dependencies respected. Concurrency configurable.\n\n#### ◇ Self-Healing Engine\nError scanner runs every 30s, groups failures by card, auto-fixes (2 attempts), escalates to a new card if it can't. Intelligence engine learns patterns, auto-labels cards, tunes timeouts.\n\n#### ◇ Rejection Learning\nWhen you reject a card, the orchestrator asks why. Your feedback is stored and injected into future brainstorm and discovery prompts. The AI adapts to your preferences over time.\n\n\u003c/td\u003e\n\u003ctd\u003e\n\n#### ◇ Real-Time Board\nSSE live updates. Drag-and-drop. 9-step progress visualization. Labels, search, diff viewer, inline file editing. Dark mode. WCAG 2.2 AAA. Keyboard shortcuts (`N` new, `/` search, `D` dark mode).\n\n#### ◇ Two-Server Security\nPublic board on `0.0.0.0`, admin panel on `127.0.0.1` (kernel-level TCP reject). Argon2id passwords, AES-256-GCM encryption, JWT auth, CSP nonce, CSRF, token bucket rate limiting. Roles: superadmin \u003e admin \u003e user.\n\n#### ◇ Production Ops\nTiered backups (5min / hourly / daily). Factory reset. Health probes (`/health`, `/health/ready`). Structured JSON logging (pino). Heartbeat watchdog. Graceful shutdown with pipeline drain.\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cbr\u003e\n\n## ◆ Deploy\n\n| Method | Command | Use case |\n|:------:|---------|----------|\n| **Local** | `scripts/start.sh` | Dev, testing |\n| **GCP Ubuntu** | `sudo bash autoconfig.sh` | Production (systemd, Nginx, UFW, auto-update) |\n| **Docker** | `docker build -f deploy/Dockerfile -t claude-kanban .` | Containers |\n| **Compose** | `cd deploy \u0026\u0026 docker compose up -d` | Self-hosting |\n| **Kubernetes** | `kubectl apply -k deploy/k8s/` | Orchestrated |\n\nSee [Deployment](docs/deployment.md) for full details.\n\n\u003cbr\u003e\n\n## ◆ Trust\n\n\u003cdiv align=\"center\"\u003e\n\n**305 automated tests** across 5 suites. [View the report \u0026rarr;](public/product/trust/)\n\n| Reliability | Dependency Audit | Performance | Data Durability | Code Quality |\n|:-----------:|:----------------:|:-----------:|:---------------:|:------------:|\n| **168** | **27** | **28** | **35** | **47** |\n\n\u003c/div\u003e\n\n```bash\npnpm test              # all suites\npnpm test:reliability  # single suite\n```\n\n\u003cbr\u003e\n\n## ◆ Architecture at a Glance\n\n```\n┌─────────────────────────────────────────────────────────┐\n│                    Cloudflare Edge                       │\n│              DNS · CDN · WAF · DDoS Shield              │\n└──────────────────────┬──────────────────────────────────┘\n                       │\n         ┌─────────────┴─────────────┐\n         │                           │\n    ┌────▼────┐               ┌──────▼──────┐\n    │ Public  │               │   Admin     │\n    │ :51777  │               │  :random    │\n    │ 0.0.0.0 │               │ 127.0.0.1   │\n    │         │               │ (TCP reject │\n    │ Board   │               │  external)  │\n    │ API     │               │             │\n    │ SSE     │               │ Control     │\n    │ Auth    │               │ Backups     │\n    └────┬────┘               │ Users       │\n         │                    └──────┬──────┘\n         │                           │\n    ┌────▼───────────────────────────▼────┐\n    │          SQLite (WAL mode)          │\n    │  cards · sessions · audit_log      │\n    │  users · config · error_log        │\n    │  learnings · checkpoints           │\n    │  claude_usage                       │\n    └──────────────────┬─────────────────┘\n                       │\n    ┌──────────────────▼─────────────────┐\n    │           Service Layer            │\n    │  Pipeline · Brainstorm · Review    │\n    │  Auto-discover · Intelligence      │\n    │  Snapshot · Git · Claude Runner    │\n    └────────────────────────────────────┘\n```\n\n\u003cbr\u003e\n\n## ◆ Documentation\n\n| | Document | What's Inside |\n|-|----------|---------------|\n| ◇ | [Architecture](docs/architecture.md) | Two-server design, service layer, database schema |\n| ◇ | [Pipeline](docs/pipeline.md) | Build-review-ship cycle, auto-fix loop, self-healing |\n| ◇ | [API Reference](docs/api.md) | 100 endpoints with request/response examples |\n| ◇ | [Configuration](docs/configuration.md) | 70+ environment variables, custom prompts |\n| ◇ | [Deployment](docs/deployment.md) | Local, Docker, K8s, GCP autoconfig |\n| ◇ | [Security Audit](docs/security-audit.md) | Three audits, 35 findings + 72 CodeQL alerts fixed |\n\n\u003cbr\u003e\n\n## ◆ Tech Stack\n\n| Layer | Choice | Why |\n|-------|--------|-----|\n| Runtime | Node.js \u0026ge; 18 | Zero-config, cross-platform |\n| Server | Express | 5 deps, no framework overhead |\n| Database | SQLite (WAL) | Single file, zero ops, instant backups |\n| Auth | Argon2id + JWT + AES-256-GCM | Password hashing, tokens, field encryption |\n| Frontend | Vanilla JS | No build step, 150KB total, ships as-is |\n| Logging | Pino | Structured JSON, correlation IDs |\n| CI | GitHub Actions | Matrix: Ubuntu/Windows, Node 18/22 |\n\n\u003cbr\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n## ◆ License\n\n[Apache 2.0](LICENSE) -- [Divya Mohan](https://dmj.one)\n\nSee [NOTICE](NOTICE) for attribution requirements.\n\n---\n\n\u003csub\u003e◆ Built with care. Ships with confidence. ◆\u003c/sub\u003e\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivyamohan1993%2Fclaude-kanban","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdivyamohan1993%2Fclaude-kanban","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivyamohan1993%2Fclaude-kanban/lists"}