Provides persistent, local-first project memory for AI coding agents to store and retrieve architectural decisions, debugging lessons, and conventions.
Also known as vasikmansuri/devmemory, @vasikmansuri/devmemory
- Stars
- 14
- Tools
- 9
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 2, 2026
- License
- MIT
What is devmemory MCP?
devmemory provides persistent, local-first project memory for AI coding agents to store and retrieve architectural decisions, debugging lessons, and conventions. It exposes 9 tools, such as memory_save, memory_search, memory_get.
Summary generated from the project's README
About devmemory MCP server
DevMemory provides a local-first way for AI coding agents to maintain long-term memory of project-specific information. It allows tools like Claude Code and Cursor to store and retrieve architectural decisions, debugging lessons, and coding conventions across different sessions. By using the Model Context Protocol via stdio, the server ensures that your AI assistant does not forget critical context every time a new conversation begins.
The system operates entirely on your machine using a local SQLite database stored in your home directory. It does not require an account, cloud connection, or telemetry. To ensure security, the server redacts sensitive information like API keys and passwords before they are saved. It also treats retrieved memories as untrusted data to protect against prompt injection. Developers can manage this memory through a dedicated CLI with 15 commands or through 9 specific MCP tools including memory_save, memory_search, and memory_context.
What you can do with it
- 1Preserve architectural decisionsInstruct an AI agent to save a specific technology choice so it can be recalled in future sessions.
- 2Avoid repeating debugging stepsStore a lesson learned from a difficult bug to prevent the AI from making the same mistake again.
- 3Enforce team coding standardsProvide the AI with project-specific conventions and constraints to ensure consistent code generation.
- 4Automate knowledge managementUse the command line interface to programmatically import or export project memory as JSON.
Written from the project's README. Every use case is checked against a quote from it.
How to install devmemory MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall devmemory MCP in Claude Code
$ claude mcp add devmemory -- npx -y @vasikmansuri/devmemoryInstall devmemory MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"devmemory": {
"command": "npx",
"args": [
"-y",
"@vasikmansuri/devmemory"
]
}
}
}Install devmemory MCP in VS Code
.vscode/mcp.json
{
"servers": {
"devmemory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vasikmansuri/devmemory"
]
}
}
}Install devmemory MCP in VS Code CLI
$ code --add-mcp '{"name":"devmemory","type":"stdio","command":"npx","args":["-y","@vasikmansuri/devmemory"]}'Install devmemory MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"devmemory": {
"command": "npx",
"args": [
"-y",
"@vasikmansuri/devmemory"
]
}
}
}Install devmemory MCP in Codex
$ codex mcp add devmemory -- npx -y @vasikmansuri/devmemoryInstall devmemory MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.devmemory] command = "npx" args = ["-y", "@vasikmansuri/devmemory"]
Install devmemory MCP in Gemini CLI
$ gemini mcp add -s user devmemory npx -- -y @vasikmansuri/devmemoryInstall devmemory MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"devmemory": {
"command": "npx",
"args": [
"-y",
"@vasikmansuri/devmemory"
]
}
}
}devmemory MCP tools 9
Detected from the READMEmemory_savememory_searchmemory_getmemory_updatememory_forgetmemory_listmemory_contextmemory_linkmemory_stats
| memory_save | — | |
| memory_search | — | |
| memory_get | — | |
| memory_update | — | |
| memory_forget | — | |
| memory_list | — | |
| memory_context | — | |
| memory_link | — | |
| memory_stats | — |
Automated checks
Ran Nov 13, 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 reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHub🧠 DevMemory
Persistent, local-first memory for AI coding agents. An MCP server and CLI for Claude Code, Cursor and other MCP clients.
Stop re-explaining your codebase. DevMemory remembers your project's decisions, architecture, debugging lessons and conventions across AI sessions. It runs 100% on your machine.
Quick start · Claude Code · Cursor · MCP tools · CLI · Security · Docs
✨ Why DevMemory?
AI coding assistants like Claude Code and Cursor forget everything when a session ends. Every new conversation, you explain the same architecture, the same "we tried X and it broke", the same team conventions.
DevMemory gives your AI agent long-term project memory through the Model Context Protocol (MCP):
| Without DevMemory | With DevMemory | |
|---|---|---|
| 🗂️ Project decisions | Re-explained every session | Saved once, retrieved automatically |
| 🐛 Debugging lessons | Rediscovered the hard way | Recalled when the same symptom appears |
| 📏 Conventions & constraints | Forgotten mid-task | Included in every relevant context bundle |
| 🔒 Privacy | Context pasted into chats | Stored locally in SQLite, never uploaded |
🚀 Features
- 🏠 Local-first and private. A single SQLite file at
~/.devmemory/. No cloud, no account, no telemetry, no network port. - 🔌 MCP server. 9 tools over stdio, verified with Claude Code. Works with any MCP client.
- 🗃️ Project-scoped memory. Each repository's knowledge is isolated, and no project can read another's.
- 🏷️ Structured memory types: decisions, architecture, debugging lessons, conventions, constraints, task context and facts. Each memory has tags, importance, confidence and an optional expiry.
- 🔎 Fast, explainable search. SQLite FTS5 full-text search with BM25 ranking, weighted by importance, confidence and recency. Every result explains its score.
- 🧾 Provenance. Every memory records where it came from: source, client, file, PR or commit reference, and timestamps.
- 🔐 Secret redaction. API keys, tokens, passwords and private keys are redacted before anything is stored.
- 🛡️ Prompt-injection aware. Retrieved memories are wrapped as untrusted data, and instruction-like content is flagged.
- ♻️ Safe lifecycle. Duplicate detection, conflict surfacing, supersede chains, reversible archiving, and hard deletes that also purge the search index.
- 📦 Import and export. Portable JSON with validation, size limits and protection against path traversal and symlinks.
- 🧰 Developer CLI. 15 commands, JSON output and meaningful exit codes for automation.
🏗️ How it works
flowchart LR
subgraph Clients
CC[🤖 Claude Code]
CU[🖱️ Cursor]
CLI[⌨️ devmemory CLI]
end
subgraph DevMemory["DevMemory (local process)"]
MCP[MCP server<br/>9 tools · stdio]
ENG[Memory engine]
SEC[🔐 Secret redaction<br/>+ validation]
RET[🔎 FTS5 / BM25<br/>ranking]
end
DB[(SQLite<br/>~/.devmemory/devmemory.db)]
CC -- JSON-RPC over stdio --> MCP
CU -- JSON-RPC over stdio --> MCP
CLI --> ENG
MCP --> ENG
ENG --> SEC --> DB
ENG --> RET --> DB
Memory across sessions
sequenceDiagram
actor Dev as Developer
participant S1 as Session 1 (Claude Code)
participant DM as DevMemory
participant S2 as Session 2 (new day)
Dev->>S1: "We chose Drizzle over Prisma because of edge runtimes"
S1->>DM: memory_save(type: decision, ...)
DM-->>S1: ✅ saved (secrets redacted, provenance recorded)
Note over S1: Session ends, the agent forgets everything
Dev->>S2: "Add a new database table"
S2->>DM: memory_context("database table")
DM-->>S2: 📋 Drizzle decision + conventions (with provenance)
S2-->>Dev: Uses Drizzle correctly, without being re-told
⚡ Quick start
Requires Node.js ≥ 22.12.
# 1. Install
npm install -g @vasikmansuri/devmemory
# 2. Verify the CLI is available
devmemory --version
# 3. Register your project
cd ~/code/my-app
devmemory init
# 4. Save knowledge
devmemory remember -t decision --title "Use Drizzle ORM" \
-c "Drizzle over Prisma: Prisma's engine binary breaks on edge runtimes." \
--tags db,orm -i 4 --source-ref docs/adr/0003.md
# 5. Find it again
devmemory search "which orm"
devmemory context "touching the data layer"
git clone https://github.com/vasikmansuri/devmemory.git
cd devmemory
npm ci && npm run build && npm link
devmemory --version
🤖 Connect Claude Code
✅ Verified end to end with Claude Code 2.1.294.
claude mcp add --transport stdio devmemory -- devmemory mcp
Share it with your team via .mcp.json:
claude mcp add --scope project --transport stdio devmemory -- devmemory mcp
Check the connection with claude mcp list or /mcp. Then try "Save to DevMemory: we deploy with Argo CD", start a new session, and ask "how do we deploy?"
💡 Claude Code starts the server in your working directory, and DevMemory finds the nearest registered project automatically, even from subfolders.
🖱️ Connect Cursor
⚠️ Configuration follows Cursor's documented format, but has not been tested end to end yet. Add this to .cursor/mcp.json:
{
"mcpServers": {
"devmemory": {
"type": "stdio",
"command": "devmemory",
"args": ["mcp", "--project", "${workspaceFolder}"]
}
}
}
🧩 MCP tools
| Tool | Description |
|---|---|
memory_save |
Save a memory. Reports duplicates and possible conflicts; can supersede older memories. |
memory_search |
Ranked keyword search with type, tag and status filters. |
memory_get |
Fetch one memory with links and lifecycle history. |
memory_update |
Edit in place; previous values are kept in history. |
memory_forget |
Archive (reversible) or permanently delete (confirm: true). |
memory_list |
Paginated, filtered listing. |
memory_context |
A token-budgeted context bundle for the current task. |
memory_link |
Relate memories: depends_on, conflicts_with, … |
memory_stats |
Project statistics. |
⌨️ CLI reference
| Command | Purpose |
|---|---|
devmemory init |
Register the current directory as a project |
devmemory remember |
Save a memory (-c - reads stdin) |
devmemory search <query> |
Ranked keyword search |
devmemory get <id> |
Full memory with provenance and history |
devmemory list |
Browse with filters and pagination |
devmemory context [query] |
The context bundle an agent receives |
devmemory update <id> |
Edit a memory |
devmemory forget <id> |
Archive, or --hard --yes to delete |
devmemory link <a> <b> |
Link two memories |
devmemory stats · projects · doctor |
Statistics, project list, health checks |
devmemory export · import |
Portable JSON backup and restore |
devmemory mcp |
Run the MCP server (stdio) |
Add --json to any command for machine-readable output.
Exit codes: 0 ok · 1 internal error · 2 validation · 3 not found · 4 project not initialized · 5 conflict · 6 database error · 7 I/O or unsafe path.
📊 Search quality (measured, not claimed)
These numbers come from 36 labelled queries over a 46-memory test project (npm run eval):
| Metric | All queries | Direct wording | Paraphrased |
|---|---|---|---|
| Recall@5 | 0.944 | 1.000 | 0.750 |
| MRR | 0.922 | 1.000 | 0.650 |
| Precision@5 (max achievable 0.228) | 0.217 | 0.229 | 0.175 |
DevMemory uses keyword search, not semantic search, so paraphrased questions with no shared words can miss. Semantic search is on the roadmap.
🔐 Security & privacy
- ✅ Runs locally: no telemetry, no network listener, no external API calls.
- ✅ Secrets are redacted before storage, covering AWS keys, GitHub tokens, OpenAI and Anthropic keys, JWTs, private keys and passwords.
- ✅ The database file is readable only by your user (mode
0600). - ✅ Projects are isolated, and all SQL is parameterized.
- ✅ Retrieved memories are treated as untrusted data, never as instructions.
- ⚠️ The database is not encrypted at rest. Use full-disk encryption for extra protection.
Read more in the security model and SECURITY.md.
⚙️ Configuration
| Variable | Default | Purpose |
|---|---|---|
DEVMEMORY_HOME |
~/.devmemory |
Data directory |
DEVMEMORY_PROJECT |
current dir | Project to use |
DEVMEMORY_SECRET_POLICY |
redact |
redact or reject writes containing secrets |
DEVMEMORY_EXTRA_TYPES |
— | Extra memory types, comma-separated |
DEVMEMORY_LOG_LEVEL |
warn |
Log level (stderr only) |
📚 Documentation
Architecture · Memory model · Security model · MCP integration · Troubleshooting · Retrieval evaluation · Roadmap · Contributing · Changelog
🛣️ Roadmap
- Local MCP server, CLI, FTS5 search, secret redaction, project isolation
- Verified Claude Code integration
- Optional local embeddings for semantic search
- End-to-end verified Cursor integration
- Better tokenization for Chinese and Japanese text
- Opt-in encryption at rest
🤝 Contributing
Contributions are welcome! Run npm run check (typecheck, lint, 129 tests, build) and see CONTRIBUTING.md.
⚠️ Known limitations
- Keyword search only (no semantic search yet).
- Chinese and Japanese text is tokenized coarsely.
- Moving a project folder requires running
devmemory initagain. - The Cursor integration is unverified.
📄 License
MIT © Vasik Mansuri
If DevMemory saves you from re-explaining your codebase, please ⭐ star the repo!
Keywords: AI memory · MCP server · Model Context Protocol · Claude Code memory · Cursor MCP · AI coding assistant · persistent context · long-term memory for LLM agents · local-first · SQLite FTS5 · developer tools
Support
If this project is useful to you, you can support my open-source work:
devmemory MCP questions
How do I add devmemory MCP to Claude Code?
Run claude mcp add devmemory -- npx -y @vasikmansuri/devmemory in your terminal. Add --scope user to make it available in every project.
How do I add devmemory 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 devmemory MCP provide?
It exposes 9 tools, including memory_save, memory_search, memory_get, memory_update, memory_forget.
How does it handle sensitive information like API keys?
The server performs secret redaction, covering AWS keys, GitHub tokens, and other private credentials before anything is stored.
Does it support semantic search?
Currently, it uses SQLite FTS5 full-text keyword search rather than semantic search, though semantic search is on the roadmap.
Can I use it with Claude Code?
Yes, it is verified end-to-end with Claude Code.