io.github.tathagat22/slipstream
io.github.tathagat22/slipstream
Shared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.
timeout probed 2026-10-15 · HTTP 200
probe timed out after 15000 ms
- Endpoint
- https://slipstream-pi.vercel.app/api/mcp (streamable-http)
- Host
- slipstream-pi.vercel.app
- Repository
- https://github.com/tathagat22/slipstream
- Website
- https://slipstream-pi.vercel.app
- Registry
- active, updated 2026-06-01 · registry entry
- Reachable
- 6 of the last 6 probes
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 16:32 | alive | 729 ms | 8 | 2.1k | 1.2k |
| 2026-10-05 00:56 | alive | 340 ms | 8 | 1.2k | |
| 2026-10-04 10:07 | alive | 1.0 s | 8 | 1.2k | |
| 2026-10-04 08:00 | alive | 742 ms | 8 | 1.2k | |
| 2026-10-03 20:40 | alive | 2.6 s | 8 | 1.2k | |
| 2026-10-03 17:55 | alive | 579 ms | 8 | 1.2k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.tathagat22/slipstream)
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.