Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite. That is what the remem mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
remem is a single Rust binary that automatically captures, distills, searches, and injects project memory across Claude Code, OpenAI Codex, and Codex CLI sessions. It keeps decisions, bug-fix rationale, project patterns, and preferences available through hooks, MCP, CLI, and REST without requiring an external database.
The server publishes 13 tools. What each one is for:
Bug — fix rationale, preferences, and project patterns are searchableCurrent — memory contracts expose staleness, temporal/as-of truth, citationUser — context controls keep personal claims, profile summaries, suppressionHomebrew — brew install majiayu000/tap/rememcrates.io — cargo install remem-ai --bin rememFailure — loop learning**: raw transcripts that contain both concreteCapability — Claude Code / Codex CLIWindows — SupportedCapture — Automatic hooks + LLM distillationAgents — Claude Code + Codex, one shared storeStorage — Local SQLite, optional SQLCipher encryptionRetrieval — FTS + optional embeddings via CLI, MCP, RESTBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Configuration is passed through the environment: OPENAI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Remem's toolset — Bug, Current, User and 10 more — is a fair guide to whether it matches your workflow. It is maintained by majiayu000; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Bug | fix rationale, preferences, and project patterns are searchable. |
| Current | memory contracts expose staleness, temporal/as-of truth, citation |
| User | context controls keep personal claims, profile summaries, suppression |
| Homebrew | brew install majiayu000/tap/remem |
| crates.io | cargo install remem-ai --bin remem |
| Failure | loop learning**: raw transcripts that contain both concrete |
| Capability | Claude Code / Codex CLI |
| Windows | Supported |
| Capture | Automatic hooks + LLM distillation |
| Agents | Claude Code + Codex, one shared store |
| Storage | Local SQLite, optional SQLCipher encryption |
| Retrieval | FTS + optional embeddings via CLI, MCP, REST |
| Runtime | Single Rust binary |
{
"mcpServers": {
"remem": {
"command": "npx",
"args": ["-y", "@remem-ai/remem"],
"env": {
"OPENAI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.