Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
If you already use Audrey, the audrey mcp server is the piece that lets your assistant work with it directly. Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
Memory that shows up before your coding agent makes the same mistake twice.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Development — The Development tool exposed by this serverBecause 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: AUDREY_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY, AUDREY_HOST, ZEP_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.
audrey - Python client: audrey-memory - Default storage: local SQLite + FTS5 + sqlite-vec - Default embeddings: local 384-dimensional model For a project install with npm 12, approve Audrey's reviewed dependency scripts in the project root and rebuild once if npm reported that it blocked them: For Autopilot, prefer a global or otherwise stable installation. HookAmong the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Audrey's toolset — Development — is a fair guide to whether it matches your workflow. It is maintained by Evilander; 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 |
|---|---|
| Development | The Development tool exposed by this server. |
{
"mcpServers": {
"audrey": {
"command": "npx",
"args": ["-y", "audrey"],
"env": {
"AUDREY_API_KEY": "your-value",
"ANTHROPIC_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value",
"AUDREY_HOST": "your-value",
"ZEP_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
audrey - Python client: audrey-memory - Default storage: local SQLite + FTS5 + sqlite-vec - Default embeddings: local 384-dimensional model For a project install with npm 12, approve Audrey's reviewed dependency scripts in the project root and rebuild once if npm reported that it blocked them: For Autopilot, prefer a global or otherwise stable installation. Hook| Variable | Description | Required |
|---|---|---|
| AUDREY_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| AUDREY_HOST | Endpoint or connection string the server talks to. | Optional |
| ZEP_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.