Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
Most knowledge and memory work still happens through a UI a human drives. Pensyve MCP server moves it into the conversation instead. Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
Universal memory runtime for AI agents. Framework-agnostic, protocol-native, offline-first.
The server publishes 8 tools. What each one is for:
Variable — DefaultPENSYVE_API_KEYS — (empty)PENSYVE_VALIDATION_URL — (none)PENSYVE_RATE_LIMIT — 300HOST — 0.0.0.0PORT — 3000Core — The Core tool exposed by this serverBenchmarks — The Benchmarks tool exposed by this serverConfiguration is passed through the environment: PENSYVE_PATH, PENSYVE_API_KEY, PENSYVE_VALIDATION_URL, PENSYVE_REMOTE_URL, DATABASE_URL, REDIS_URL, PENSYVE_TIER2_MODEL_PATH. 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.
Because 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.
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. Pensyve's toolset — Variable, PENSYVE_API_KEYS, PENSYVE_VALIDATION_URL and 5 more — is a fair guide to whether it matches your workflow. It is maintained by major7apps; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Pensyve's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Variable | Default |
| PENSYVE_API_KEYS | _(empty)_ |
| PENSYVE_VALIDATION_URL | _(none)_ |
| PENSYVE_RATE_LIMIT | 300 |
| HOST | 0.0.0.0 |
| PORT | 3000 |
| Core | The Core tool exposed by this server. |
| Benchmarks | The Benchmarks tool exposed by this server. |
```json
{
"mcpServers": {
"pensyve": {
"command": "./target/release/pensyve-mcp",
"env": { "PENSYVE_PATH": "~/.pensyve/default" }
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PENSYVE_PATH | Filesystem location the server is allowed to use. | Optional |
| PENSYVE_API_KEY | Credential the server authenticates with. | Yes |
| PENSYVE_VALIDATION_URL | Endpoint or connection string the server talks to. | Yes |
| PENSYVE_REMOTE_URL | Endpoint or connection string the server talks to. | Yes |
| DATABASE_URL | Endpoint or connection string the server talks to. | Yes |
| REDIS_URL | Endpoint or connection string the server talks to. | Yes |
| PENSYVE_TIER2_MODEL_PATH | Filesystem location the server is allowed to use. | Optional |
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.