io.github.remembra-ai/remembra
Remembra Relay
Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.
alive probed 2026-10-14
24tools
12ktokens in Claude Opus 5.5
12ktokens in Claude Code
6.0 %of a 200k context window
7.1ko200k_base estimate
3.2 sto initialize
9 msto list tools
- Run it
- uvx remembra-mcp==0.16.2 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- remembra 0.16.2
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- 1 295 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/remembra-ai/remembra
- Website
- https://remembra.dev
- Registry
- active, updated 2026-10-10 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| recall_memories | 699 | 10 % |
| close_session | 682 | 10 % |
| session_brief | 634 | 9 % |
| forget_memories | 476 | 7 % |
| timeline | 460 | 6 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.remembra-ai/remembra)
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.