Provides a shared memory layer that allows connected AI coding agents to store and recall learned context across different sessions and tools.
Also known as thomasjumper/agentbay, agentbay, aiagentsbay-mcp
- Stars
- 2
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 1.2.5
- Last commit
- Nov 9, 2026
- License
- MIT
What is StremAI MCP?
StremAI provides a shared memory layer that allows connected AI coding agents to store and recall learned context across different sessions and tools. It exposes 4 tools, such as agentbay_local_unavailable, agentbay_signup, agentbay_capabilities.
Summary generated from the project's README
About StremAI MCP server
StremAI provides a shared memory layer designed for AI coding agents to retain and share learned context. It allows different agents to store information such as architectural decisions, repository conventions, and technical pitfalls so that subsequent sessions or different tools can recall them. This prevents developers from having to repeat the same explanations to every new agent session or when switching between different machines.
Users can connect the service to MCP-compatible clients like Claude Code, Cursor, Codex, Windsurf, and OpenClaw. The primary connection method is via a hosted endpoint using OAuth or browser sign-in. For environments like CI or clients that do not support browser authentication, developers can use API keys with a Bearer header. A local fallback is also available through npm or PyPI for stdio-only clients. The system ensures memory is human-readable and attributed to the specific agent that created the entry.
What you can do with it
- 1Share context across different toolsAn agent can store a learned fix in one tool so that another coding assistant can access it later.
- 2Maintain knowledge across sessionsPrevent context from disappearing when you start a new session or move to a different computer.
- 3Automate repository knowledge transferStore specific repository commands and setup instructions for future agent use.
- 4Manage learned architectural patternsRecord specific technical decisions like authentication patterns to ensure consistency.
Written from the project's README. Every use case is checked against a quote from it.
How to install StremAI MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall StremAI MCP in Claude Code
$ claude mcp add agentbay -- npx -y aiagentsbay-mcpInstall StremAI MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentbay": {
"command": "npx",
"args": [
"-y",
"aiagentsbay-mcp"
]
}
}
}Install StremAI MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentbay": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"aiagentsbay-mcp"
]
}
}
}Install StremAI MCP in VS Code CLI
$ code --add-mcp '{"name":"agentbay","type":"stdio","command":"npx","args":["-y","aiagentsbay-mcp"]}'Install StremAI MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentbay": {
"command": "npx",
"args": [
"-y",
"aiagentsbay-mcp"
]
}
}
}Install StremAI MCP in Codex
$ codex mcp add agentbay -- npx -y aiagentsbay-mcpInstall StremAI MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentbay] command = "npx" args = ["-y", "aiagentsbay-mcp"]
Install StremAI MCP in Gemini CLI
$ gemini mcp add -s user agentbay npx -- -y aiagentsbay-mcpInstall StremAI MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentbay": {
"command": "npx",
"args": [
"-y",
"aiagentsbay-mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for aiagentsbay-mcp 1.2.5 in an isolated container with no network and no keys. It answered and listed 4 tools.
StremAI MCP tools 4
Read from the server with tools/listagentbay_local_unavailableRead-onlyDiagnostic: local AgentBay memory is OFF in this session because no SQLite driver loaded (better-sqlite3 native binary missing and Node < 22.5 has no built-in node:sqlite). The memory tools are hidden until this is fixed. Call this tool for the exact reason and the fixes: upgrade Node to >= 22.5, rebuild better-sqlite3, or set AGENTBAY_API_KEY for cloud mode.
agentbay_signupActionStart the signup flow. Cloud mode needs no local SQLite, so signing up also fixes the unavailable local memory on this machine.
agentbay_capabilitiesRead-onlyIntrospect this AgentBay MCP connection: surface, available tools, and how to restore local memory.
agentbay_whoamiRead-onlyShow your current authentication status.
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablethomasjumper/agentbay is public and reachablegithub.com/thomasjumper/agentbay ↗Pass
- Package names this repository as its sourceaiagentsbay-mcp names thomasjumper/agentbay as sourcenpmjs.com/package/aiagentsbay-mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-09github.com/thomasjumper/agentbay ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from aiagentsbay-mcpPass
- No critical advisory in the package or its dependencies134 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubStremAI
One brain for all your coding agents.
StremAI 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.
Memory is user-controlled: entries are human-readable, attributed to the agent that stored them, and can be exported, archived, or erased from StremAI.
Use StremAI when
- You keep re-explaining the same repo, conventions, or decisions to every new agent session
- Context disappears between sessions, or when you switch machines
- One agent learns something — a pitfall, a fix, an architectural decision — and your other agents have no idea
- Handoff notes go stale and nothing tells an agent which version still applies
- You use more than one coding tool and want them to share context instead of starting from zero
The short version
- Hosted MCP first. Connect
https://stremai.com/api/mcpwith OAuth/browser sign-in where your MCP client supports it. - Works with the tools developers already use. Claude Code, Cursor, Codex, Windsurf, OpenClaw, Hermes, and other MCP clients can use the same memory layer.
- API keys are the fallback. Use them for CI, scripts, or clients that cannot complete OAuth/browser sign-in.
- Compatibility names remain. Some packages and tools still use the original
agentbayoraiagentsbay-mcpnames so existing installs keep working.
Connect Claude Code
claude mcp add --transport http stremai https://stremai.com/api/mcp --scope user
Then approve the sign-in in your browser. The --scope user flag makes the connection available outside the current project directory.
Connect another MCP client
Use the hosted endpoint:
{
"mcpServers": {
"stremai": {
"type": "http",
"url": "https://stremai.com/api/mcp"
}
}
}
If your client cannot complete OAuth/browser sign-in, create an API key in StremAI and use a Bearer header:
{
"mcpServers": {
"stremai": {
"type": "http",
"url": "https://stremai.com/api/mcp",
"headers": {
"Authorization": "Bearer ab_live_your_key_here"
}
}
}
}
Local package fallback
For stdio-only clients or local experiments:
npx -y aiagentsbay-mcp@latest
The package name is legacy compatibility; new docs and server aliases use stremai.
Python:
pip install stremai
from stremai import StremAI
brain = StremAI()
brain.store("JWT auth uses 24h refresh tokens", title="Auth pattern", type="PATTERN")
brain.recall("authentication")
What StremAI remembers
StremAI is for the learned layer that accumulates while agents work:
- decisions and architectural context
- setup gotchas and repo-specific commands
- pitfalls that cost time once and should not cost time again
- handoffs between Claude Code, Cursor, Codex, and teammates
- project facts that should be available to the next connected agent
Keep your instruction files. CLAUDE.md, AGENTS.md, and project READMEs hold instructions you write. StremAI holds the memory agents learn while working.
Useful entry points
- Website: stremai.com
- MCP docs: stremai.com/docs/mcp-memory
- Claude Code memory: stremai.com/docs/claude-code-memory
- Python SDK: stremai.com/docs/python-sdk
- AI answer inventory: stremai.com/llms-full.txt
Install guides
Comparison reads
About this repo
This is StremAI's public install, comparison, scorecard, and MCP recipe surface. The repository name remains agentbay for compatibility with older links and package metadata.
The 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.
License
MIT for everything in this repository.
StremAI MCP questions
How do I add StremAI MCP to Claude Code?
Run claude mcp add agentbay -- npx -y aiagentsbay-mcp in your terminal. Add --scope user to make it available in every project.
How do I add StremAI MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does StremAI MCP provide?
It exposes 4 tools, including agentbay_local_unavailable, agentbay_signup, agentbay_capabilities, agentbay_whoami.
What can StremAI remember?
It stores learned information such as architectural decisions, setup gotchas, repository-specific commands, and project pitfalls.
Can I use StremAI if my client doesn't support OAuth?
Yes, you can use API keys as a fallback for CI, scripts, or clients that cannot complete browser sign-in.
Is the memory user-controlled?
Yes, entries are human-readable, attributed to the agent that stored them, and can be exported, archived, or erased.