An open-source AI memory layer that actually remembers what matters. Local-first, batteries-included, and opinionated about not forgetting your
Widemem Ai MCP server exists for a simple reason — assistants are far more useful when they can act on Widemem Ai directly instead of describing what you should do. An open-source AI memory layer that actually remembers what matters. Local-first, batteries-included, and opinionated about not forgetting your user's blood type.
Once Widemem Ai is connected, these are the calls the assistant has available:
Function — Formulaexponential — e^(-rate * days)linear — max(1 - rate * days, 0)step — 1.0 / 0.7 / 0.4 / 0.1 at 7/30/90 daysnone — Always 1.0Tiers — Query routing uses keyword heuristics (no extra LLM call) with a fallback chain. If the preferred tier has no results, it falls back to the nextYou will need one environment variable: QDRANT_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
widemem-ai on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Plenty of AI and media services 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. Widemem Ai's toolset — Function, exponential, linear and 3 more — is a fair guide to whether it matches your workflow. It is maintained by remete618; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Function | Formula |
| exponential | e^(-rate * days) |
| linear | max(1 - rate * days, 0) |
| step | 1.0 / 0.7 / 0.4 / 0.1 at 7/30/90 days |
| none | Always 1.0 |
| Tiers | Query routing uses keyword heuristics (no extra LLM call) with a fallback chain. If the preferred tier has no results, it falls back to the next tier. No results left behind. |
{
"mcpServers": {
"widemem-ai": {
"command": "uvx",
"args": ["widemem-ai"],
"env": {
"QDRANT_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| QDRANT_URL | Endpoint or connection string the server talks to. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.