{
  "markdown": "<div align=\"center\">\n\n# SidClaw\n\n**Approve, deny, and audit AI agent tool calls.**\n\nWorks with MCP, LangChain, OpenAI Agents, Claude Agent SDK, and 15+ more.\n\n[![GitHub stars](https://img.shields.io/github/stars/sidclawhq/platform?style=flat-square&color=F59E0B)](https://github.com/sidclawhq/platform/stargazers)\n[![npm version](https://img.shields.io/npm/v/@sidclaw/sdk?style=flat-square&color=3B82F6)](https://www.npmjs.com/package/@sidclaw/sdk)\n[![PyPI version](https://img.shields.io/pypi/v/sidclaw?style=flat-square&color=3B82F6&label=PyPI)](https://pypi.org/project/sidclaw/)\n[![License: Apache-2.0](https://img.shields.io/badge/SDK-Apache%202.0-22C55E?style=flat-square)](LICENSE)\n[![License: FSL](https://img.shields.io/badge/Platform-FSL%201.1-F59E0B?style=flat-square)](LICENSE-PLATFORM)\n[![Tests](https://img.shields.io/badge/tests-1050%2B%20passing-22C55E?style=flat-square)](https://github.com/sidclawhq/platform/actions)\n[![CI](https://img.shields.io/github/actions/workflow/status/sidclawhq/platform/ci.yml?style=flat-square&label=build)](https://github.com/sidclawhq/platform/actions)\n\n<a href=\"https://sidclaw.com\" target=\"_blank\">Website</a> · <a href=\"https://docs.sidclaw.com\" target=\"_blank\">Documentation</a> · <a href=\"https://demo.sidclaw.com\" target=\"_blank\">Live Demo</a> · <a href=\"https://www.npmjs.com/package/@sidclaw/sdk\" target=\"_blank\">SDK on npm</a> · <a href=\"https://pypi.org/project/sidclaw/\" target=\"_blank\">SDK on PyPI</a>\n\n</div>\n\n---\n\nYour agents call tools without oversight. SidClaw intercepts every tool call, checks it against your policies, and holds risky actions for human review before they execute.\n\n### Try it locally (10 seconds, no signup)\n\n```bash\nnpx sidclaw-demo\n```\n\nOpens a local governance dashboard at `http://localhost:3030` with four pre-loaded scenarios (Claude Code `rm -rf`, fintech trade, DevOps scale-to-zero, clinical lab order). No signup, no Docker, no API key — just the approval card UX running in your browser.\n\n### See it in action\n\n![Atlas Financial Demo](docs/assets/atlas_demo.gif)\n\n*Agent wants to send an email → policy flags it → reviewer sees full context → approves or denies → trace recorded.*\n\n## Works With Your Stack\n\n<div align=\"center\">\n\n![Integrations](docs/assets/integrations-grid.png)\n\n</div>\n\nSidClaw integrates with **18+ frameworks and platforms** — including OpenClaw (329K+ users), LangChain, OpenAI, MCP, Claude Agent SDK, Google ADK, NemoClaw, Copilot Studio, GitHub Copilot, and more. Add governance in one line of code. <a href=\"https://docs.sidclaw.com/docs/integrations\" target=\"_blank\">See all integrations →</a>\n\n## See It In Action\n\n### Customer Support Agent (Financial Services)\n\n![Atlas Financial Demo](docs/assets/atlas_demo.gif)\n\n*An AI agent wants to send a customer email. Policy flags it for review. The reviewer sees full context — who, what, why — and approves with one click. Every step is traced.*\n\n### Infrastructure Automation (DevOps)\n\n![DevOps Demo](docs/assets/devops_demo.gif)\n\n*An AI agent wants to scale production services. High-risk deployments require human approval. Read-only monitoring is allowed instantly.*\n\n### Clinical Decision Support (Healthcare)\n\n![Healthcare Demo](docs/assets/health_demo.gif)\n\n*An AI assistant recommends lab orders. The physician reviews the clinical context and approves. Medication prescribing is blocked by policy — only physicians can prescribe.*\n\n## How It Works\n\n```\nAgent wants to act → SidClaw evaluates → Policy decides → Human approves (if needed) → Action executes → Trace recorded\n```\n\nFour primitives govern every agent action:\n\n```\n┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐\n│ Identity │ →  │  Policy  │ →  │ Approval │ →  │  Trace   │\n│          │    │          │    │          │    │          │\n│ Every    │    │ Every    │    │ High-risk│    │ Every    │\n│ agent    │    │ action   │    │ actions  │    │ decision │\n│ has an   │    │ evaluated│    │ get human│    │ creates  │\n│ owner &  │    │ against  │    │ review   │    │ tamper-  │\n│ scoped   │    │ explicit │    │ with rich│    │ evident  │\n│ perms    │    │ rules    │    │ context  │    │ audit    │\n└──────────┘    └──────────┘    └──────────┘    └──────────┘\n```\n\n- **allow** → action executes immediately, trace recorded\n- **approval_required** → human sees context card, approves/denies, trace recorded\n- **deny** → blocked before execution, no data accessed, trace recorded\n\n## Deploy your own SidClaw instance ($0)\n\nRailway is the recommended one-click deploy — it spins up Postgres + API + Dashboard together. Vercel hosts only the Next.js dashboard; pair it with a hosted API.\n\n[![Deploy on Railway](https://railway.app/button.svg)](https://railway.com/new/template?template=https://github.com/sidclawhq/platform)\n\n<details>\n<summary><strong>Vercel (dashboard only — point at an existing SidClaw API)</strong></summary>\n\n```\nhttps://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fsidclawhq%2Fplatform&root-directory=apps%2Fdashboard&env=NEXT_PUBLIC_API_URL&envDescription=Your%20SidClaw%20API%20base%20URL%20(e.g.%20https%3A%2F%2Fapi.sidclaw.com)\n```\n\nVercel can only host the dashboard (Next.js). The API is Fastify — deploy it to Railway, Fly, Render, or run via Docker. Set `NEXT_PUBLIC_API_URL` on the dashboard project to point at it.\n\n</details>\n\nUnder 3 minutes to a working instance on Railway.\n\n---\n\n## Quick Start — Pick What Fits\n\n### Option 1: Claude Code Hooks (zero code)\n\nFor Claude Code users. Every `Bash`, `Write`, `Agent`, `mcp__*` tool call is governed by SidClaw:\n\n```bash\n# In the SidClaw platform repo\nnpm run hooks:install\n\n# Then set two env vars\nexport SIDCLAW_BASE_URL=https://api.sidclaw.com\nexport SIDCLAW_API_KEY=ai_your_key_here\n```\n\nRestart Claude Code. `rm -rf` pauses for approval, `git push --force` gets flagged, every tool call is traced with a hash-chained audit trail. See [hooks/README.md](hooks/README.md).\n\n### Option 2: `create-sidclaw-app` (interactive scaffold)\n\n```bash\nnpx create-sidclaw-app my-agent\ncd my-agent\nnpm start\n```\n\n### Option 3: MCP Governance Proxy (zero code, wraps any MCP server)\n\nJump to the [MCP Governance Proxy section below](#mcp-governance-proxy).\n\n### Option 4: SDK wrapper (one line per tool)\n\n```typescript\n// Before: the agent decides, nobody reviews\nawait sendEmail({ to: \"customer@example.com\", subject: \"Follow-up\", body: \"...\" });\n\n// After: wrap with SidClaw — now policies apply\nconst sendEmail = withGovernance(client, {\n  operation: 'send_email',\n  data_classification: 'confidential',\n}, sendEmailFn);\n\nawait sendEmail({ to: \"customer@example.com\", subject: \"Follow-up\", body: \"...\" });\n// → allow (executes) | approval_required (human reviews) | deny (blocked)\n```\n\n<details>\n<summary>Same thing in Python</summary>\n\n```python\n@with_governance(client, GovernanceConfig(\n    operation=\"send_email\",\n    data_classification=\"confidential\",\n))\ndef send_email(to, subject, body):\n    email_service.send(to=to, subject=subject, body=body)\n```\n</details>\n\n<details>\n<summary><strong>Full TypeScript example with imports</strong></summary>\n\n```bash\nnpm install @sidclaw/sdk\n```\n\n```typescript\nimport { AgentIdentityClient, withGovernance } from '@sidclaw/sdk';\n\nconst client = new AgentIdentityClient({\n  apiKey: process.env.SIDCLAW_API_KEY,\n  apiUrl: 'https://api.sidclaw.com',\n  agentId: process.env.SIDCLAW_AGENT_ID,\n});\n\nconst sendEmail = withGovernance(client, {\n  operation: 'send_email',\n  target_integration: 'email_service',\n  resource_scope: 'customer_emails',\n  data_classification: 'confidential',\n}, async (to, subject, body) => {\n  await emailService.send({ to, subject, body });\n});\n\nawait sendEmail('customer@example.com', 'Follow-up', 'Hello...');\n// allow → executes | approval_required → waits for human | deny → throws\n```\n\n</details>\n\n<details>\n<summary><strong>Full Python example with imports</strong></summary>\n\n```bash\npip install sidclaw\n```\n\n```python\nimport os\nfrom sidclaw import SidClaw\nfrom sidclaw.middleware.generic import with_governance, GovernanceConfig\n\nclient = SidClaw(\n    api_key=os.environ[\"SIDCLAW_API_KEY\"],\n    agent_id=os.environ[\"SIDCLAW_AGENT_ID\"],\n)\n\n@with_governance(client, GovernanceConfig(\n    operation=\"send_email\",\n    target_integration=\"email_service\",\n    data_classification=\"confidential\",\n))\ndef send_email(to, subject, body):\n    email_service.send(to=to, subject=subject, body=body)\n```\n\n</details>\n\n## MCP Governance Proxy\n\nWrap any MCP server with policy evaluation and approval workflows. Works with Claude Desktop, Cursor, VS Code, GitHub Copilot — any MCP client. Listed on the <a href=\"https://registry.modelcontextprotocol.io\" target=\"_blank\">official MCP Registry</a>.\n\nAdd to your `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"postgres-governed\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@sidclaw/sdk\", \"sidclaw-mcp-proxy\", \"--transport\", \"stdio\"],\n      \"env\": {\n        \"SIDCLAW_API_KEY\": \"ai_your_key\",\n        \"SIDCLAW_AGENT_ID\": \"your-agent-id\",\n        \"SIDCLAW_UPSTREAM_CMD\": \"npx\",\n        \"SIDCLAW_UPSTREAM_ARGS\": \"-y,@modelcontextprotocol/server-postgres,postgresql://localhost/mydb\"\n      }\n    }\n  }\n}\n```\n\n- `SELECT * FROM customers` → **allowed** (~50ms overhead)\n- `DELETE FROM customers WHERE id = 5` → **held for human approval**\n- `DROP TABLE customers` → **denied by policy**\n\n<a href=\"https://docs.sidclaw.com/docs/integrations/claude-code\" target=\"_blank\">Full MCP governance docs →</a>\n\n## Why not just auth / sandboxing / logging?\n\n| Approach | What it solves | What it doesn't solve |\n|----------|---------------|----------------------|\n| **Auth (Okta, OAuth)** | Who is this agent? | Should this specific action execute right now? |\n| **Sandboxing (Docker, WASM)** | Blast radius if something goes wrong | Whether the action should happen at all |\n| **Logging (Langfuse, LangSmith)** | What happened after the fact | Intercepting actions before they execute |\n| **Policy engines (OPA)** | General-purpose policy evaluation | Approval workflows, agent-specific context, audit trails |\n| **SidClaw** | All of the above, plus the **Approval** primitive | — |\n\nSidClaw sits at the **tool-call layer**: the moment an agent decides to act in the real world.\n\n## Integrations\n\nSidClaw wraps your existing agent tools — no changes to your agent logic.\n\n### Agent Frameworks\n\n| | TypeScript | Python |\n|--|-----------|--------|\n| Core client | `@sidclaw/sdk` | `sidclaw` |\n| MCP proxy | `@sidclaw/sdk/mcp` | `sidclaw.mcp` |\n| LangChain | `@sidclaw/sdk/langchain` | `sidclaw.middleware.langchain` |\n| OpenAI Agents | `@sidclaw/sdk/openai-agents` | `sidclaw.middleware.openai_agents` |\n| CrewAI | `@sidclaw/sdk/crewai` | `sidclaw.middleware.crewai` |\n| Vercel AI | `@sidclaw/sdk/vercel-ai` | — |\n| Pydantic AI | — | `sidclaw.middleware.pydantic_ai` |\n| Claude Agent SDK | `@sidclaw/sdk/claude-agent-sdk` | `sidclaw.middleware.claude_agent_sdk` |\n| Google ADK | `@sidclaw/sdk/google-adk` | `sidclaw.middleware.google_adk` |\n| LlamaIndex | `@sidclaw/sdk/llamaindex` | `sidclaw.middleware.llamaindex` |\n| Composio | `@sidclaw/sdk/composio` | `sidclaw.middleware.composio` |\n| NemoClaw | `@sidclaw/sdk/nemoclaw` | `sidclaw.middleware.nemoclaw` |\n| Webhooks | `@sidclaw/sdk/webhooks` | `sidclaw.webhooks` |\n\n### Platform Integrations\n\n| Integration | Description |\n|---|---|\n| **Claude Code** | Govern any MCP server in Claude Code. Add a `.mcp.json` entry — zero code changes. <a href=\"https://docs.sidclaw.com/docs/integrations/claude-code\" target=\"_blank\">Guide →</a> |\n| **OpenClaw** | Governance proxy for OpenClaw skills. Published as `sidclaw-governance` on ClawHub. <a href=\"https://docs.sidclaw.com/docs/integrations/openclaw\" target=\"_blank\">Guide →</a> |\n| **MCP** | Governance proxy for any MCP server. Listed on the <a href=\"https://registry.modelcontextprotocol.io\" target=\"_blank\">official MCP Registry</a>. CLI binary (`sidclaw-mcp-proxy`) + programmatic API. <a href=\"https://docs.sidclaw.com/docs/integrations/mcp\" target=\"_blank\">Guide →</a> |\n| **NemoClaw** | Govern NVIDIA NemoClaw sandbox tools with MCP-compatible proxy generation. <a href=\"https://docs.sidclaw.com/docs/integrations/nemoclaw\" target=\"_blank\">Guide →</a> |\n| **Copilot Studio** | Governance for Microsoft Copilot Studio skills via OpenAPI action. <a href=\"https://docs.sidclaw.com/docs/integrations/copilot-studio\" target=\"_blank\">Guide →</a> |\n| **GitHub Copilot** | Governance for GitHub Copilot agents via HTTP transport. <a href=\"https://docs.sidclaw.com/docs/integrations/github-copilot\" target=\"_blank\">Guide →</a> |\n| **GitHub Action** | `sidclawhq/governance-action@v1` — reusable CI governance step. <a href=\"https://docs.sidclaw.com/docs/integrations/github-action\" target=\"_blank\">Guide →</a> |\n\n### Notification Channels\n\nApproval requests are delivered to your team's preferred channels. Reviewers can approve or deny directly from chat.\n\n| Channel | Features |\n|---|---|\n| **Slack** | Block Kit messages with interactive Approve/Deny buttons. Messages update in-place after decision. |\n| **Microsoft Teams** | Adaptive Card notifications with Approve/Deny buttons (Bot Framework) or dashboard links (webhook). |\n| **Telegram** | HTML messages with inline keyboard. Callback updates remove buttons and add reply. |\n| **Resend** | Email notifications for approval requests via transactional email. |\n\n## Licensing\n\n| Component | License | What you can do |\n|-----------|---------|----------------|\n| SDK (`@sidclaw/sdk`, `sidclaw` on PyPI) | Apache 2.0 | Use freely, modify, distribute, commercial use |\n| MCP Proxy (`sidclaw-mcp-proxy`) | Apache 2.0 | Same as SDK |\n| Platform (API, Dashboard, Docs) | FSL 1.1 | Free for orgs under CHF 1M revenue. Converts to Apache 2.0 in 2028 |\n\n**Start with just the SDK?** You don't need the platform. The SDK works standalone with the free hosted API at <a href=\"https://app.sidclaw.com/signup\" target=\"_blank\">app.sidclaw.com</a>, or you can <a href=\"https://docs.sidclaw.com/docs/enterprise/self-hosting\" target=\"_blank\">self-host everything</a>.\n\n## Why This Exists\n\nAI agents are being deployed in production, but the governance layer is missing:\n\n- **73% of CISOs** fear AI agent risks, but only **30%** are ready (<a href=\"https://neuraltrust.ai/guides/the-state-of-ai-agent-security-2026\" target=\"_blank\">NeuralTrust 2026</a>)\n- **79% of enterprises** have blind spots where agents act without oversight\n- **FINRA 2026** explicitly requires \"documented human checkpoints\" for AI agent actions in financial services\n- **EU AI Act** mandates human oversight, automatic logging, and risk management for high-risk AI systems — obligations apply from **2 December 2027** (Annex III) and **2 August 2028** (product-embedded), deferred from August 2026 by the 2026 Digital Omnibus\n- **OpenClaw** has 329K+ stars and 13,700+ skills — but <a href=\"https://thehackernews.com/2026/02/researchers-find-341-malicious-clawhub.html\" target=\"_blank\">1,184 malicious skills were found</a> in the ClawHavoc campaign. There's no policy layer governing what skills can do.\n\nThe big vendors (Okta, SailPoint, WorkOS) handle identity and authorization. But none of them ship the **approval step** — the part where a human sees rich context and makes an informed decision before an agent acts.\n\n### Compliance\n\nSidClaw maps to regulatory requirements across the US, EU, Switzerland, and Singapore:\n\n🇺🇸 <a href=\"https://docs.sidclaw.com/docs/compliance/finra-2026\" target=\"_blank\">FINRA 2026</a> · 🇪🇺 <a href=\"https://docs.sidclaw.com/docs/compliance/eu-ai-act\" target=\"_blank\">EU AI Act</a> · 🇨🇭 <a href=\"https://docs.sidclaw.com/docs/compliance/finma\" target=\"_blank\">FINMA</a> · 🇸🇬 <a href=\"https://docs.sidclaw.com/docs/compliance/mas-trm\" target=\"_blank\">MAS TRM</a> · 🇺🇸 <a href=\"https://docs.sidclaw.com/docs/compliance/nist-ai-rmf\" target=\"_blank\">NIST AI RMF</a> · 🌐 <a href=\"https://docs.sidclaw.com/docs/compliance/owasp-agentic\" target=\"_blank\">OWASP Agentic</a>\n\n## Platform Features\n\n### For Developers\n- **60-second setup** — `npx create-sidclaw-app` scaffolds a working governed agent\n- **<50ms evaluation overhead** — the governance layer is invisible to your users\n- **5-minute integration** — wrap existing tools, no code changes\n- **MCP-native** — governance proxy for any MCP server\n- **Framework-agnostic** — LangChain, Vercel AI, OpenAI, CrewAI, Pydantic AI, Composio, Claude Agent SDK, Google ADK, LlamaIndex, NemoClaw, or plain functions\n- **Typed SDKs** — TypeScript (npm) + Python (PyPI)\n\n### For Security & Compliance Teams\n- **Policy engine** — allow / approval_required / deny with priority ordering and classification hierarchy\n- **Approval workflow** — context-rich cards with agent reasoning, risk classification, and separation of duties\n- **Audit trails** — correlated traces with integrity hash chains (tamper-evident)\n- **SIEM export** — JSON and CSV, continuous webhook delivery\n\n### For Platform Teams\n- **RBAC** — admin, reviewer, viewer roles with enforced permissions\n- **Tenant isolation** — automatic tenant scoping on every query\n- **API key management** — scoped keys with rotation\n- **Rate limiting** — per-tenant, per-endpoint-category\n- **Webhooks** — real-time notifications for approvals, traces, lifecycle events\n- **Chat integrations** — approve/deny from Slack, Teams, or Telegram without opening the dashboard\n- **Self-serve signup** — GitHub, Google, email/password\n\n## Architecture\n\n```\n┌─────────────┐     ┌──────────────┐     ┌──────────────────┐\n│ Your Agent  │     │  SidClaw SDK │     │  SidClaw API     │\n│             │ ──► │              │ ──► │                  │\n│ LangChain   │     │ evaluate()   │     │ Policy Engine    │\n│ MCP Server  │     │ withGovern() │     │ Approval Service │\n│ OpenAI SDK  │     │ governTools()│     │ Trace Store      │\n│ Any tool    │     │              │     │ Webhook Delivery │\n└─────────────┘     └──────────────┘     └──────────────────┘\n                                                   │\n                                          ┌────────┴────────┐\n                                          ▼                 ▼\n                                ┌──────────────┐  ┌──────────────┐\n                                │  Dashboard   │  │ Notifications│\n                                │              │  │              │\n                                │ Agents       │  │ Slack        │\n                                │ Policies     │  │ Teams        │\n                                │ Approvals    │  │ Telegram     │\n                                │ Traces       │  │ Email        │\n                                │ Settings     │  │ Webhooks     │\n                                └──────────────┘  └──────────────┘\n```\n\n## Deploy\n\n### One-Click Deploy\n\n[![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/new/github?repo=sidclawhq/platform)\n\nDeploy from the GitHub repo to Railway. Add a PostgreSQL database, configure environment variables, and you're live.\n\n[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fsidclawhq%2Fplatform&root-directory=apps/dashboard&env=NEXT_PUBLIC_API_URL&envDescription=SidClaw%20API%20URL&envLink=https%3A%2F%2Fdocs.sidclaw.com%2Fdocs%2Fenterprise%2Fself-hosting&project-name=sidclaw-dashboard&repository-name=sidclaw-dashboard)\n\nDeploy the dashboard to Vercel (requires a separately hosted API).\n\n<details>\n<summary>Deploy Docs or Landing Page to Vercel</summary>\n\n**Docs:**\n\n[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fsidclawhq%2Fplatform&root-directory=apps/docs&project-name=sidclaw-docs&repository-name=sidclaw-docs)\n\n**Landing Page:**\n\n[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fsidclawhq%2Fplatform&root-directory=apps/landing&project-name=sidclaw-landing&repository-name=sidclaw-landing)\n\n</details>\n\n### Self-Host (Docker)\n\n```bash\ncurl -sSL https://raw.githubusercontent.com/sidclawhq/platform/main/deploy/self-host/setup.sh | bash\n```\n\nOr manually:\n\n```bash\ngit clone https://github.com/sidclawhq/platform.git\ncd platform\ncp deployment/env.example .env  # edit with your values\ndocker compose -f docker-compose.production.yml up -d\n```\n\n**Development credentials:**\n- Email: `admin@example.com` / Password: `admin`\n- Or click **\"Sign in with SSO\"** on the login page to auto-login without a password\n\n### Hosted Cloud\n\nNo infrastructure to manage. <a href=\"https://app.sidclaw.com/signup\" target=\"_blank\">Start free at app.sidclaw.com</a>\n\nSee <a href=\"https://docs.sidclaw.com/docs/enterprise/self-hosting\" target=\"_blank\">deployment documentation</a> for production configuration, environment variables, and upgrade guides.\n\n## Documentation\n\n- <a href=\"https://docs.sidclaw.com/docs/quickstart\" target=\"_blank\">Quick Start</a> — 2 minutes to first governed action\n- <a href=\"https://docs.sidclaw.com/docs/sdk/client\" target=\"_blank\">SDK Reference</a> — every method documented\n- <a href=\"https://docs.sidclaw.com/docs/integrations\" target=\"_blank\">Integrations</a> — MCP, OpenClaw, NemoClaw, LangChain, OpenAI, Claude Agent SDK, Google ADK, Copilot Studio, GitHub Copilot, and more\n- <a href=\"https://docs.sidclaw.com/docs/platform/policies\" target=\"_blank\">Policy Guide</a> — authoring, versioning, testing\n- <a href=\"https://docs.sidclaw.com/docs/compliance/finra-2026\" target=\"_blank\">Compliance</a> — 🇺🇸 FINRA · 🇪🇺 EU AI Act · 🇨🇭 FINMA · 🇸🇬 MAS TRM · 🇺🇸 NIST AI RMF · 🌐 OWASP\n- <a href=\"https://docs.sidclaw.com/docs/api-reference\" target=\"_blank\">API Reference</a> — every endpoint\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\nThe SDK (`packages/sdk/`) is Apache 2.0. The platform (`apps/`) is FSL 1.1.\n\n## License\n\n- **SDK** (`packages/sdk/`, `packages/shared/`): [Apache License 2.0](LICENSE) — use freely for any purpose\n- **Platform** (`apps/api/`, `apps/dashboard/`, `apps/docs/`, `apps/landing/`, `apps/demo*/`): [Functional Source License 1.1](LICENSE-PLATFORM) — source-available. Cannot offer as a competing hosted service. Converts to Apache 2.0 after 2 years (March 2028).\n\n## Links\n\n- <a href=\"https://sidclaw.com\" target=\"_blank\">Website</a>\n- <a href=\"https://docs.sidclaw.com\" target=\"_blank\">Documentation</a>\n- <a href=\"https://app.sidclaw.com\" target=\"_blank\">Dashboard</a>\n- <a href=\"https://www.npmjs.com/package/@sidclaw/sdk\" target=\"_blank\">TypeScript SDK (npm)</a>\n- <a href=\"https://pypi.org/project/sidclaw/\" target=\"_blank\">Python SDK (PyPI)</a>\n- <a href=\"https://github.com/sidclawhq/python-sdk\" target=\"_blank\">Python SDK (GitHub)</a>\n- <a href=\"https://www.npmjs.com/package/create-sidclaw-app\" target=\"_blank\">create-sidclaw-app (npm)</a>\n- <a href=\"https://github.com/sidclawhq/governance-action\" target=\"_blank\">GitHub Action</a>\n- <a href=\"https://github.com/apps/sidclaw-governance\" target=\"_blank\">GitHub App</a>\n- <a href=\"mailto:hello@sidclaw.com\">Contact</a>\n",
  "bytes": 23054,
  "sha": "7dbb392c3dc0c553aa7b6fe8b8c071b9d1c55b4b021707abc62341d0f7021c84",
  "repo_slug": "sidclawhq/platform",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_vladuzh_sidclaw_governance_mcp_920c3470/readme"
}