60-second local start
pipx install + hebb setup + hebb service install. SQLite + sentence-transformers, zero external services. No API key needed for ingest and hybrid search.
A memory framework for AI agents — named for Donald Hebb, whose rule the brain learns by: neurons that fire together, wire together.
In 1949, Canadian psychologist Donald O. Hebb (1904–1985) described the rule the brain learns by. Hebb Mind is built on it.
Hebb's insight: a memory is not a place — it is a pattern of connection. Concepts that co-occur wire into cell assemblies; a partial cue lights up the rest. Hebb Mind's tag knowledge graph runs exactly that loop.
And the hippocampus — the project's original name? It lives on as the working-memory partition (mem_hippocampus): the inbox every new memory enters before consolidation, just as the brain's hippocampus gates new experience into long-term memory. The brain region became one component; the learning rule became the name.
Four stages, in roughly the order the brain runs them — encoding in CA1, replay during slow-wave sleep (Wilson & McNaughton, Science, 1994), pattern-completion in CA3, and the forgetting curve (Ebbinghaus, 1885) doing its quiet work.
pipx install hebb-mind && hebb setup && hebb service installpipx yet? One-time setup (brew / apt / dnf / python -m pip). Then open http://localhost:8321/. For LLM consolidation, see the 5-minute path.Core capabilities you'd expect — plus what only we do.
| Feature | Mem0 | Letta | Zep | Hebb Mind |
|---|---|---|---|---|
| Multi-model support | Yes | Yes | Yes | Via LiteLLM |
| Knowledge graph | Pluggable (removed in v3) | No | Yes (Graphiti) | Tag-based (NetworkX) |
| Self-hosted Web UI | Cloud only | Cloud only | Cloud only | Built-in SPA |
| MCP Server | Yes | Consumer only | Yes | Built-in, auto-start |
| Memory consolidation | ADD-only | Sleeptime Agent | Contradiction resolve | Automatic + conflict resolve |
| Forgetting / decay | No | No | Temporal invalidation | Dynamic TTL |
| Zero-config deploy | API key required | API key + DB | Postgres + Neo4j | SQLite + local embed |