dev.workers.notdown-app.recall/memory
Recall — persistent memory for agents
Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.
alive probed 2026-10-05 · HTTP 200
5tools
529tokens in Claude Opus 5.5
564tokens in Claude Code
0.3 %of a 200k context window
284o200k_base estimate
233 msto initialize
209 msto list tools
- Endpoint
- https://recall.notdown-app.workers.dev/mcp/{key} (streamable-http)
- Host
- recall.notdown-app.workers.dev
- Protocol
- 2025-11-25
- Reports itself as
- Recall 0.1.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
- Website
- https://recall.notdown-app.workers.dev
- Registry
- active, updated 2026-08-25 · registry entry
- Reachable
- 6 of the last 6 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| memory_save | 114 | 40 % |
| memory_search | 57 | 20 % |
| memory_recall | 40 | 14 % |
| memory_forget | 37 | 13 % |
| memory_list | 36 | 13 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 14:02 | alive | 233 ms | 5 | 529 | 284 |
| 2026-10-05 00:25 | alive | 354 ms | 5 | 284 | |
| 2026-10-04 10:00 | alive | 162 ms | 5 | 284 | |
| 2026-10-04 07:54 | alive | 150 ms | 5 | 284 | |
| 2026-10-03 20:33 | alive | 230 ms | 5 | 284 | |
| 2026-10-03 17:50 | alive | 333 ms | 5 | 284 |
Badge and feed
[](https://mcpcost.ulehla.dev/s/dev.workers.notdown-app.recall/memory)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.