agentsmd-memory
MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.
README
agentsmd-memory
MCP server for keeping project memory in AGENTS.md. Zero dependencies.
The tools don't edit files. They resolve the nearest AGENTS.md and return merge instructions; the agent applies them with its own edit tools, so changes show up as a git diff.
Tools
memory_save— record a durable fact (decision, convention, gotcha, non-obvious command).memory_forget— remove a stale fact.
Install
Published on npm as agentsmd-memory. Runs via npx — no global install needed. Add to your MCP client's config:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "agentsmd-memory"]
}
}
}
opencode uses mcp with "type": "local"; Claude Code: claude mcp add --transport stdio memory -- npx -y agentsmd-memory. Windows: wrap as cmd /c npx -y agentsmd-memory.
opencode plugin (recommended)
The tools are prompt-driven — the agent only calls them if it decides to, which rarely happens mid-task. The package also ships an opencode plugin that injects a short reminder into the system prompt every turn, so the agent reliably reaches for memory_save/memory_forget. Enable it alongside the MCP server:
{
"plugin": ["agentsmd-memory"]
}
Config
| Env | Default | Purpose |
|---|---|---|
MEMORY_FILE |
AGENTS.md |
Target file name, e.g. CLAUDE.md, GEMINI.md. Bare name only. |
Notes
- Workspace dir is resolved from MCP roots, else a
cwdarg, elseprocess.cwd(). From there it walks up to the git root; nearest existing file wins. - The tools never write files. When no memory file exists,
memory_savereturns instructions to create one; the agent authors it with its own Write tool, so even bootstrapping shows up as a reviewable diff. - Saves are prompt-driven; the agent decides when to call them. The bundled opencode plugin nudges it every turn.
Develop
npm test
npx @modelcontextprotocol/inspector npx -y agentsmd-memory
Source: github.com/jryom/agentsmd-memory.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.