{
  "markdown": "# Memside\n\nMemside is an AI continuity and memory hub for work across ChatGPT, Claude, Grok, IDEs, coding agents, and other AI tools that support OAuth, MCP, or API-key connections. It provides a private place for reusable context, decisions, Operating Rules, project notes, checkpoints, and Library Templates that can move between compatible AI tools.\n\nMemside keeps AI context available beyond one chat window. A connected AI tool can retrieve relevant memories, continue a project from a checkpoint, follow saved working preferences, create approved durable context, and work with permission-controlled Library Templates. This repository is the public home for Memside integration documentation, examples, SDKs, and support information. It is not a mirror of the private production application source.\n\nProduct site: [https://www.memside.com](https://www.memside.com)\n\nDocumentation: [https://docs.memside.com](https://docs.memside.com)\n\n## Continuity With Less Repeated Prompting\n\nMemside is built to give AI assistants the right context at the right time:\ncurrent task state, saved preferences, project notes, checkpoints, and reusable\nrules. In internal testing and early pilot usage, this helped AI tools stay on\ntrack without requiring users to rebuild the same detailed prompt in every new\nchat or IDE session.\n\nHigh-level test results:\n\n| Context approach | Continuity score |\n| --- | ---: |\n| No Context | ~45% |\n| Long Context Dump | ~84-85% |\n| Memside Context | ~96-99% |\n| Very Detailed Manual Prompt | ~97-99% |\n\n**Token savings:** in separate context-reuse tests, Memside reduced repeated\nfull-context transfer by **83-91%** on representative light, medium, and heavy\nproject datasets.\n\nA very detailed manual prompt means a long prompt where the user includes every\nimportant detail by hand: project state, preferences, decisions, references, and\nnext steps. With Memside, the workflow is simpler: ask the AI to save the\ncheckpoint, references, and useful context, then move to a new chat and ask it\nto continue from that checkpoint using Memside.\n\nResults are based on internal tests and early pilot usage patterns. Performance\nvaries by model, provider, prompt style, and workflow. See\n[Continuity and context results](docs/continuity-results.md) for details.\n\n## Connect Memside\n\nMemside supports hosted MCP access for AI tools that can connect to remote MCP servers. MCP gives compatible AI clients a standard way to use Memside as a continuity layer instead of locking memory into one assistant.\n\n```text\nhttps://api.memside.com/mcp/\n```\n\nFor AI tools that support OAuth for MCP, setup continues through Memside sign-in. AI tools that support API-key authentication can use a Memside API key as a bearer token.\n\nStart here:\n\n- [Official documentation](https://docs.memside.com/)\n- [Developer quickstart](docs/developer-quickstart.md)\n- [JavaScript SDK](packages/memside/README.md)\n- [Python SDK](packages/python/README.md)\n- [Capabilities](docs/capabilities.md)\n- [Continuity and context results](docs/continuity-results.md)\n- [Token savings and context reuse](docs/token-savings.md)\n- [Memory types and sensitivity](docs/memory-types.md)\n- [Connect AI clients](docs/clients/README.md)\n- [Client support matrix](docs/client-support.md)\n- [Install in VS Code](docs/clients/vscode.md)\n- [Use Memside with API keys](docs/api-keys.md)\n- [Public API reference](docs/public-api.md)\n- [Memside Library and Templates](docs/template-library.md)\n- [Curated OpenAPI document](openapi.json)\n- [MCP Registry metadata](docs/mcp-registry.md)\n- [Directory metadata](docs/mcp-registry.md#third-party-directory-metadata)\n- [Troubleshooting](docs/troubleshooting.md)\n\n## Developer Quickstart\n\nSelect the path that matches the client or integration.\n\n| Goal | Use | Start here |\n| --- | --- | --- |\n| Connect ChatGPT, Grok, Claude, or another hosted client | OAuth MCP | [Client guides](docs/clients/README.md) |\n| Connect IDEs and coding agents such as VS Code, Copilot, Cursor, Claude Code, Codex, Antigravity, opencode, or a local MCP client | Bearer-header MCP | [VS Code guide](docs/clients/vscode.md) |\n| Call Memside from scripts or automation | API key | [API keys](docs/api-keys.md) |\n\nFor a direct API check, create a Memside API key and run:\n\n```bash\ncurl https://api.memside.com/context/startup \\\n  -H \"Authorization: Bearer mem_sk_example_key\"\n```\n\nFor a runnable JavaScript example:\n\n```bash\ncd examples/javascript\nnpm run startup\n```\n\nSet `MEMSIDE_API_KEY` before running examples. See [Developer quickstart](docs/developer-quickstart.md) for the full setup.\n\n## JavaScript SDK\n\nMemside publishes a lightweight JavaScript SDK for public API-key workflows:\n\n```bash\nnpm install memside\n```\n\nBasic usage:\n\n```js\nimport { MemsideClient } from \"memside\";\n\nconst memside = new MemsideClient({\n  apiKey: process.env.MEMSIDE_API_KEY\n});\n\nconst startup = await memside.context.startup();\nconsole.log(startup);\n```\n\nThe JavaScript SDK wraps public Memside API routes for startup context, resume\ncontext, workspace profile, Memory operations, Subject organization, and\nLibrary Template workflows. See\n[packages/memside](packages/memside/README.md) for package details.\n\n## Python SDK\n\nMemside also publishes a lightweight Python SDK for public API-key workflows:\n\n```bash\npip install memside\n```\n\nBasic usage:\n\n```python\nfrom memside import MemsideClient\n\nclient = MemsideClient(api_key=\"mem_sk_example_key\")\n\nstartup = client.context_startup()\nprint(startup)\n```\n\nThe Python SDK wraps the same public Memside API areas as the JavaScript SDK. See [packages/python](packages/python/README.md) for package details.\n\n## MCP Server Setup\n\nUse this hosted MCP server URL in clients that support remote MCP:\n\n```text\nhttps://api.memside.com/mcp/\n```\n\nFor ChatGPT, Grok, Claude, and other clients that offer OAuth during MCP setup, choose OAuth and complete Memside sign-in.\n\nFor clients that use bearer headers, create a Memside API key and pass it as:\n\n```text\nAuthorization: Bearer mem_sk_example_key\n```\n\nVS Code and GitHub Copilot can use a workspace `.vscode/mcp.json` file:\n\n```json\n{\n  \"servers\": {\n    \"memside\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.memside.com/mcp/\",\n      \"headers\": {\n        \"Authorization\": \"Bearer mem_sk_example_key\"\n      }\n    }\n  }\n}\n```\n\nKeep real API keys out of shared files. Use local user-level configuration or secret storage when the config is shared with a team.\n\nDetailed setup guides are available for [VS Code](docs/clients/vscode.md), [GitHub Copilot](docs/clients/github-copilot.md), [ChatGPT](docs/clients/chatgpt.md), [Grok](docs/clients/grok.md), [Claude Code](docs/clients/claude-code.md), [Cursor](docs/clients/cursor.md), [Codex](docs/clients/codex.md), [Antigravity](docs/clients/antigravity.md), and [opencode](docs/clients/opencode.md).\n\n## MCP Registry\n\nThis repository includes `server.json` for the official MCP Registry. It describes Memside as a hosted remote MCP server using Streamable HTTP at:\n\n```text\nhttps://api.memside.com/mcp/\n```\n\nThe registry entry is published under:\n\n```text\nio.github.memside/memside\n```\n\nSee [MCP Registry metadata](docs/mcp-registry.md) for registry and endpoint checks.\n\nThis repository also includes lightweight third-party directory metadata for Glama, Open Plugins, and Cursor plugin discovery. These files point to the same hosted MCP server URL and do not contain credentials.\n\n## Supported Workflows\n\nWith Memside connected, an AI tool can search saved memories, fetch specific context, create approved memories, update checkpoints, and build compact startup or resume packets. The goal is to keep useful context portable without turning every AI conversation into a long manual setup step.\n\nThis supports project movement between ChatGPT, Claude, Grok, IDEs, coding agents, and other compatible AI clients. The next AI can retrieve the project purpose, prior decisions, applicable rules, and current next step.\n\nMemside Library adds reusable Templates for profiles, Operating Rules, AI\nSkills, memories, references, examples, and repeatable workflows. Public\ncatalog discovery is read-only. Permission-controlled creator operations can\nsearch Templates, read owned drafts, replace drafts safely, and manage reviewed\npublication workflows. See [Memside Library and Templates](docs/template-library.md).\n\nMemside keeps the normal product boundary intact. Private user data is scoped to the signed-in user, secret memories are excluded from AI-facing MCP and API-key flows, and destructive actions require stronger confirmation.\n\n## Key Features\n\nMemside is designed around continuity, selective context retrieval, and user control. The core features are:\n\n- [Startup and resume context](docs/token-savings.md) for compact handoffs.\n- [Operating Rules](docs/operating-rules.md) for durable behavior guidance.\n- [User AI Profile](docs/user-ai-profile.md) for personal working preferences.\n- [AI Skills](docs/ai-skills.md) for reusable instruction packs.\n- [Public, private, and secret memories](docs/memory-types.md) for practical data boundaries.\n- [MCP and API-key access](docs/clients/README.md) for connecting multiple AI clients.\n- [Memside Library and Templates](docs/template-library.md) for reusable AI setup and creator workflows.\n\n## API Examples\n\nThe examples in this repo use public Memside API surfaces only.\n\n- [curl examples](examples/curl/README.md)\n- [JavaScript examples](examples/javascript/README.md)\n- [Python examples](examples/python/README.md)\n\nThe JavaScript and Python examples use normal HTTP requests against public Memside API surfaces.\n\nThe machine-readable [OpenAPI document](openapi.json) contains only the\napproved API-key contract. It excludes signed-in application, account,\nadministration, billing, and infrastructure operations.\n\n## Public Repo Scope\n\nThis repo contains:\n\n- setup guides for MCP clients\n- MCP Registry metadata\n- third-party MCP directory metadata\n- Cursor plugin metadata\n- technical product capability docs\n- API-key usage examples\n- developer quickstart and runnable examples\n- public troubleshooting notes\n- security and support information\n- public changelog entries\n- public Library and Template integration guidance\n\nThis repo does not contain:\n\n- private Memside application source\n- secrets or deployment configuration\n- database or internal operations notes\n- non-public product architecture\n\n## Support\n\nFor support, contact [support@memside.com](mailto:support@memside.com) or use the support links in the Memside app.\n\nSecurity reports should follow [SECURITY.md](SECURITY.md).\n\n## Copyright and Use\n\nCopyright (c) 2026 Memside. All rights reserved.\n\nThis repository is public documentation, not open-source application code. See [LICENSE.md](LICENSE.md) for the repository terms.\n\nMemside and related names, product concepts, documentation, and branding remain the property of their respective owners.\n",
  "bytes": 10883,
  "sha": "167bf489648a2668244be42d45fc7444c5ae27c704cdf1c0fed787d5d207e6f7",
  "repo_slug": "memside/memside",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_memside_memside_681fed8d/readme"
}