io.github.komakeule57-maker/frugal-memory
frugal-memory
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
alive probed 2026-10-21
8tools
≈ 2.5ktokens, estimate
≈ 1.2 %of Claude's 200k window
1.8×the median server
3.2 sto initialize
6 msto list tools
- Run it
- uvx frugal-memory==0.1.4 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- memory 0.1.4
- Capabilities
- prompts, resources, tools
- Instructions
- none
- Of a 1M window
- ≈ 0.2 % of a 1M context window, estimate
- Repository
- https://github.com/komakeule57-maker/frugal-memory
- Registry
- active, updated 2026-10-19 · registry entry
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| recall | 532 | 22 % |
| pruefe | 435 | 18 % |
| themen | 410 | 17 % |
| verdichten | 318 | 13 % |
| remember | 279 | 11 % |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers initialize and tools/list. Nothing to fix.