io.github.Yarmoluk/ckg-nvidia-ai
NVIDIA AI CKG
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
timeout probed 2026-10-15
fetch failed | Connect Timeout Error (attempted address: ckg-nvidia-ai.onrender.com:443, timeout: 10000ms) | UND_ERR_CONNECT_TIMEOUT
- Endpoint
- https://ckg-nvidia-ai.onrender.com/mcp (streamable-http)
- Host
- ckg-nvidia-ai.onrender.com
- Repository
- https://github.com/Yarmoluk/ckg-nvidia-ai
- Registry
- active, updated 2026-07-29 · 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 14:29 | alive | 224 ms | 9 | 2.8k | 1.6k |
| 2026-10-05 00:31 | alive | 250 ms | 9 | 1.6k | |
| 2026-10-04 10:03 | alive | 1.3 s | 9 | 1.6k | |
| 2026-10-04 07:57 | alive | 1.0 s | 9 | 1.6k | |
| 2026-10-03 20:36 | alive | 1.4 s | 9 | 1.6k | |
| 2026-10-03 17:52 | alive | 608 ms | 9 | 1.6k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Yarmoluk/ckg-nvidia-ai)
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.