What it does
The publisher describes Mitos as architectural decision memory for LLM-native workflows. Decisions are stored as markdown that people can read and as a graph that agents can query.
The source gives no further detail on setup or usage.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Mitos
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.
v0.20.0As shown on registry.modelcontextprotocol.io when we last read it