Skip to content

Hebb MindMemory that wires itself.

A memory framework for AI agents — named for Donald Hebb, whose rule the brain learns by: neurons that fire together, wire together.

Why "Hebb Mind"?

In 1949, Canadian psychologist Donald O. Hebb (1904–1985) described the rule the brain learns by. Hebb Mind is built on it.

“When an axon of cell A … repeatedly or persistently takes part in firing cell B, … A's efficiency, as one of the cells firing B, is increased.” — D. O. Hebb, The Organization of Behavior (1949) · remembered as “neurons that fire together, wire together.”

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.

🔗
Wire
Co-occurring tags gain a graph edge — a cell assembly
💪
Strengthen
Each co-activation thickens the edge; consolidation keeps what's reinforced
🌐
Complete
Retrieval walks the edges — a cue recalls the whole pattern
💨
Prune
What is never co-activated weakens and fades

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.

The Memory Loop

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.

📥
Encode
Working-memory inbox (CA1 capture)
🧠
Replay & Consolidate
Agent merges, classifies, tags (sharp-wave ripples)
🔍
Retrieve
Vector + keyword + graph (pattern completion)
💨
Forget
Dynamic TTL (Ebbinghaus decay)
60-second start — no API key
pipx install hebb-mind && hebb setup && hebb service install
No pipx yet? One-time setup (brew / apt / dnf / python -m pip). Then open http://localhost:8321/. For LLM consolidation, see the 5-minute path.

Architecture

Interface Layer
REST APIMCP ServerCLIWeb Console
HEBB MIND COREWorking Memory Inbox · Consolidation Agent · Recall Agent (Agentic RAG) · Scheduler
Processing Engine
Hybrid RetrievalVector · FTS · Graph
Knowledge GraphTag-based · NetworkX
ScoringRecency · Importance · Relevance
Dynamic ForgettingEbbinghaus TTL Decay
Infrastructure
StorageSQLite + sqlite-vec · PostgreSQL + pgvector
EmbeddingLocal (sentence-transformers) · API
LLM100+ providers via LiteLLM
Memory Partitions
📚
Semantic
Facts & Knowledge
🎬
Episodic
Events & History
❤️
Preference
Likes & Dislikes
🔧
Procedural
Skills & How-to

Why Hebb Mind

Core capabilities you'd expect — plus what only we do.

FeatureMem0LettaZepHebb Mind
Multi-model supportYesYesYesVia LiteLLM
Knowledge graphPluggable (removed in v3)NoYes (Graphiti)Tag-based (NetworkX)
Self-hosted Web UICloud onlyCloud onlyCloud onlyBuilt-in SPA
MCP ServerYesConsumer onlyYesBuilt-in, auto-start
Memory consolidationADD-onlySleeptime AgentContradiction resolveAutomatic + conflict resolve
Forgetting / decayNoNoTemporal invalidationDynamic TTL
Zero-config deployAPI key requiredAPI key + DBPostgres + Neo4jSQLite + local embed

Released under the MIT License.