{
  "markdown": "# StremAI\n\n**One brain for all your coding agents.**\n\nStremAI is a shared memory layer for AI coding agents. Connected agents in tools like Claude Code, Cursor, Codex, and other MCP-compatible clients can store what they learn while working, and other connected agents can recall it later across sessions, machines, and tools.\n\nMemory is user-controlled: entries are human-readable, attributed to the agent that stored them, and can be exported, archived, or erased from StremAI.\n\n[![PyPI](https://img.shields.io/pypi/v/stremai.svg)](https://pypi.org/project/stremai/) [![npm](https://img.shields.io/npm/v/%40tmjumper%2Fstremai.svg?label=npm)](https://www.npmjs.com/package/@tmjumper/stremai) [![MCP](https://img.shields.io/npm/v/aiagentsbay-mcp.svg?label=mcp)](https://www.npmjs.com/package/aiagentsbay-mcp) [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\n## Use StremAI when\n\n- You keep re-explaining the same repo, conventions, or decisions to every new agent session\n- Context disappears between sessions, or when you switch machines\n- One agent learns something — a pitfall, a fix, an architectural decision — and your other agents have no idea\n- Handoff notes go stale and nothing tells an agent which version still applies\n- You use more than one coding tool and want them to share context instead of starting from zero\n\n## The short version\n\n- **Hosted MCP first.** Connect `https://stremai.com/api/mcp` with OAuth/browser sign-in where your MCP client supports it.\n- **Works with the tools developers already use.** Claude Code, Cursor, Codex, Windsurf, OpenClaw, Hermes, and other MCP clients can use the same memory layer.\n- **API keys are the fallback.** Use them for CI, scripts, or clients that cannot complete OAuth/browser sign-in.\n- **Compatibility names remain.** Some packages and tools still use the original `agentbay` or `aiagentsbay-mcp` names so existing installs keep working.\n\n## Connect Claude Code\n\n```bash\nclaude mcp add --transport http stremai https://stremai.com/api/mcp --scope user\n```\n\nThen approve the sign-in in your browser. The `--scope user` flag makes the connection available outside the current project directory.\n\n## Connect another MCP client\n\nUse the hosted endpoint:\n\n```json\n{\n  \"mcpServers\": {\n    \"stremai\": {\n      \"type\": \"http\",\n      \"url\": \"https://stremai.com/api/mcp\"\n    }\n  }\n}\n```\n\nIf your client cannot complete OAuth/browser sign-in, create an API key in StremAI and use a Bearer header:\n\n```json\n{\n  \"mcpServers\": {\n    \"stremai\": {\n      \"type\": \"http\",\n      \"url\": \"https://stremai.com/api/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ab_live_your_key_here\"\n      }\n    }\n  }\n}\n```\n\n## Local package fallback\n\nFor stdio-only clients or local experiments:\n\n```bash\nnpx -y aiagentsbay-mcp@latest\n```\n\nThe package name is legacy compatibility; new docs and server aliases use `stremai`.\n\nPython:\n\n```bash\npip install stremai\n```\n\n```python\nfrom stremai import StremAI\n\nbrain = StremAI()\nbrain.store(\"JWT auth uses 24h refresh tokens\", title=\"Auth pattern\", type=\"PATTERN\")\nbrain.recall(\"authentication\")\n```\n\n## What StremAI remembers\n\nStremAI is for the learned layer that accumulates while agents work:\n\n- decisions and architectural context\n- setup gotchas and repo-specific commands\n- pitfalls that cost time once and should not cost time again\n- handoffs between Claude Code, Cursor, Codex, and teammates\n- project facts that should be available to the next connected agent\n\nKeep your instruction files. `CLAUDE.md`, `AGENTS.md`, and project READMEs hold instructions you write. StremAI holds the memory agents learn while working.\n\n## Useful entry points\n\n- Website: [stremai.com](https://stremai.com)\n- MCP docs: [stremai.com/docs/mcp-memory](https://stremai.com/docs/mcp-memory)\n- Claude Code memory: [stremai.com/docs/claude-code-memory](https://stremai.com/docs/claude-code-memory)\n- Python SDK: [stremai.com/docs/python-sdk](https://stremai.com/docs/python-sdk)\n- AI answer inventory: [stremai.com/llms-full.txt](https://stremai.com/llms-full.txt)\n\n## Install guides\n\n- [Claude Code](docs/install/claude-code.md)\n- [OpenAI Codex CLI](docs/install/codex-cli.md)\n- [Cursor](docs/install/cursor.md)\n- [OpenClaw](docs/install/openclaw.md)\n- [Hermes](docs/install/hermes.md)\n\n## Comparison reads\n\n- [vs. GBrain](docs/vs/gbrain.md)\n- [vs. Mem0](docs/vs/mem0.md)\n- [vs. Letta](docs/vs/letta.md)\n- [vs. Zep](docs/vs/zep.md)\n\n## About this repo\n\nThis is StremAI's public install, comparison, scorecard, and MCP recipe surface. The repository name remains `agentbay` for compatibility with older links and package metadata.\n\nThe hosted application and some SDK implementation details are developed separately. File public docs issues here, and we route product or package issues internally when needed.\n\n## License\n\n[MIT](LICENSE) for everything in this repository.\n",
  "bytes": 4869,
  "sha": "1142e3d0de0511d8fa59f1f3b6ef77cb0f65a9b1ab451d6da1312c284f90dccf",
  "repo_slug": "thomasjumper/agentbay",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_thomasjumper_stremai_7e462b05/readme"
}