io.github.writerslogic/cogmem
cogmem
A self-improving, verifiable memory layer for AI coding agents.
alive probed 2026-10-15
8tools
1.6ktokens in Claude Opus 5.5
1.6ktokens in Claude Code
0.8 %of a 200k context window
926o200k_base estimate
865 msto initialize
4 msto list tools
- Run it
- uvx cogmem==2.7.1 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- cogmem 2.7.0
- Capabilities
- resources, tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/writerslogic/cogmem
- Registry
- active, updated 2026-07-13 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| recall | 218 | 24 % |
| note | 138 | 15 % |
| receipt | 130 | 14 % |
| status | 109 | 12 % |
| verify | 92 | 10 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.writerslogic/cogmem)
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.