{
  "markdown": "# Penfield\n\n**Persistent memory for AI agents.** Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Works with Claude, Cursor, Windsurf, Gemini CLI, and any MCP-compatible tool.\n\n---\n\n## Quick Start\n\n### Claude (Desktop, Mobile, Web)\n\nAdd as a custom connector in Settings → Connectors:\n\n```\nName: Penfield\nRemote MCP server URL: https://mcp.penfield.app\n```\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http --scope user penfield https://mcp.penfield.app\n```\n\n### Cursor\n\n**One-click install:**\n\n[Install Penfield in Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=Penfield&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1yZW1vdGUiLCJodHRwczovL21jcC5wZW5maWVsZC5hcHAvIl19)\n\nCut and paste into your browser:\n\n```\ncursor://anysphere.cursor-deeplink/mcp/install?name=Penfield&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1yZW1vdGUiLCJodHRwczovL21jcC5wZW5maWVsZC5hcHAvIl19\n```\n\nOr add manually to `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"Penfield\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://mcp.penfield.app/\"]\n    }\n  }\n}\n```\n\n### Windsurf, Cline, Roo Code, and Others\n\nAdd to your MCP configuration file:\n\n```json\n{\n  \"mcpServers\": {\n    \"Penfield\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://mcp.penfield.app/\"]\n    }\n  }\n}\n```\n\n| App | Config Location |\n|-----|-----------------|\n| Windsurf | `~/.codeium/windsurf/mcp_config.json` |\n| Cline | VS Code Settings → Cline → MCP Servers |\n| Roo Code | VS Code Settings → Roo Code → MCP Servers |\n| Zed | `~/.config/zed/settings.json` under `\"context_servers\"` |\n\n### Gemini CLI\n\n```bash\ngemini mcp add penfield -- npx -y mcp-remote https://mcp.penfield.app/\n```\n\nOr add to `~/.gemini/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"Penfield\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://mcp.penfield.app/\"]\n    }\n  }\n}\n```\n\n---\n\n## What You Get\n\n**17 tools** for persistent memory:\n\n| Category | Tools |\n|----------|-------|\n| **Memory** | `store`, `recall`, `search`, `fetch`, `update_memory` |\n| **Knowledge Graph** | `connect`, `disconnect`, `explore` |\n| **Context** | `awaken`, `reflect`, `save_context`, `restore_context`, `list_contexts` |\n| **Artifacts** | `save_artifact`, `retrieve_artifact`, `list_artifacts`, `delete_artifact` |\n\n**Hybrid search** combining BM25 (keyword), vector (semantic), and graph (connections) for recall that actually finds what you need.\n\n**Cross-platform sync** — same memory, same knowledge graph, regardless of which tool you connect from.\n\n---\n\n## How It Works\n\n1. **Sign up** at [portal.penfield.app/sign-up](https://portal.penfield.app/sign-up)\n2. **Connect** using one of the methods above\n3. **Authenticate** when prompted (OAuth flow)\n4. **Start using** — your agent now has persistent memory\n\nEvery session should start with:\n\n```\nawaken()     # Load identity and personality context\nreflect()    # Orient on recent work (default: last 7 days)\n```\n\nWithout these, your agent starts cold with no context.\n\n---\n\n## Documentation\n\n- [Tools Reference](docs/TOOLS.md) — All 17 tools with parameters and examples\n- [Memory Types](docs/MEMORY-TYPES.md) — The 11 memory types and when to use each\n- [Relationships](docs/RELATIONSHIPS.md) — The 24 relationship types for connecting memories\n- [AI Agent Guide](SKILL.md) — Instructions for AI agents using Penfield\n\n---\n\n## Use Cases\n\n**Personal assistant that remembers**\n- Your preferences compound over time\n- Picks up conversations where you left off\n- Learns how you like things done\n\n**Development workflows**\n- Track investigation threads across sessions\n- Remember architectural decisions and why they were made\n- Hand off context between coding sessions\n\n**Research and writing**\n- Build knowledge graphs of connected ideas\n- Store insights and corrections as understanding evolves\n- Checkpoint progress on long-running projects\n\n---\n\n## Also Available\n\n**OpenClaw Native Plugin** — If you use OpenClaw, the native plugin is 4-5x faster (no MCP proxy layer):\n\n```bash\nopenclaw plugins install openclaw-penfield\nopenclaw penfield login\n```\n\n[openclaw-penfield on GitHub](https://github.com/penfieldlabs/openclaw-penfield) · [openclaw-penfield on npm](https://www.npmjs.com/package/openclaw-penfield)\n\n**API** — Direct HTTP access at `api.penfield.app` for custom integrations.\n\n---\n\n## Links\n\n- MCP: [mcp.penfield.app](https://mcp.penfield.app)\n- Website: [penfield.app](https://penfield.app)\n- Portal: [portal.penfield.app](https://portal.penfield.app)\n- Cursor Directory: [cursor.directory/mcp/penfield](https://cursor.directory/mcp/penfield)\n- X: [@penfieldlabs](https://x.com/penfieldlabs)\n- GitHub: [@penfieldlabs](https://github.com/penfieldlabs)\n\n[![penfield-mcp MCP server](https://glama.ai/mcp/servers/penfieldlabs/penfield-mcp/badges/card.svg)](https://glama.ai/mcp/servers/penfieldlabs/penfield-mcp)\n\n---\n\nCopyright © 2025 Penfield™. All rights reserved.\n",
  "bytes": 5008,
  "sha": "8d833b8c7f3c6e500937dfe9a1d4dd91c07ee800fec5c80b7b7e082018e57f36",
  "repo_slug": "penfieldlabs/penfield-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_penfieldlabs_penfield_mcp_a24bbc90/readme"
}