An open engine for AI memory.
Genesys Memory is an open-source AI agent memory system from Astrix Labs: a multiplicative scoring engine, a causal graph, and a lifecycle manager giving Claude, ChatGPT, and any MCP client persistent long-term memory. The same engine that powers the hosted service — yours to run.
pip install genesys-memory, then genesys serve --backend obsidian. Genesys uses a local embedder with no API keys and starts an MCP server on http://localhost:8000/mcp with 13 memory tools registered. Calling memory_recall("onboarding preferences") returns 3 scored memories traced to their source.Why existing memory fails.
Most "memory" is a flat pile of embeddings. At volume, it buries the few things that matter and never forgets the rest.
Flat memory doesn't scale
The 500th memory buries the 5 that matter. Vector search returns noise at volume.
No forgetting = no intelligence
Without active pruning, your agent drowns in stale context it should have let go of.
No causal reasoning
Vector similarity can't answer "why did I choose X?" For that, you need a graph.
Scoring, lifecycle, and a causal graph.
Three mechanisms work together so the right memories surface, the stale ones fade, and every recall can explain itself.
Earn the recall.
× connectivity
× reactivation
Multiplicative, not additive. A zero in any dimension sends the score to zero — no free rides.
Forget on purpose.
Memories move through states over time. Core memories are promoted and protected; the rest decay unless they keep earning their place.
Answer "why?"
Memories connect by typed edges — not just embedding similarity. Traverse the graph to reconstruct how a decision was actually reached.
Run it your way.
Same engine, four backends. Start in-memory, scale to Postgres, or keep everything local.
In-Memory
Zero dependencies. Try it out in seconds.
Postgres + pgvector
Production-ready and scalable.
Obsidian vault
Local-first. Your files stay untouched.
FalkorDB
Graph-native traversal.
GENESYS_EMBEDDER=local — no API keys needed.85.55 on LoCoMo.
Certified over 10 runs under the strictest published protocol — ahead of every published alternative. We publish our failure ledger too.
| System | LoCoMo score |
|---|---|
| Genesys | 85.55 |
| Zep | 75.1 |
| Mem0 | 67.1 |
Every operation is an MCP tool.
Works with Claude Code, Claude Desktop, OpenAI Codex, and any MCP-compliant client.
| memory_store | Store a new memory |
| memory_amend | Record a correction that supersedes a memory |
| memory_recall | Recall top-scored memories |
| memory_search | Semantic search over memories |
| memory_traverse | Walk the causal graph |
| memory_explain | Explain why a memory was recalled |
| memory_stats | Usage and lifecycle statistics |
| pin_memory | Pin a memory to prevent decay |
| unpin_memory | Unpin a memory |
| delete_memory | Permanently delete a memory |
| list_core_memories | List core memories |
| set_core_preferences | Set core memory categories |
| promote_to_org | Promote a memory to org visibility |
Up and running, fully local.
Obsidian vault setup — no API keys. Four steps from install to a memory-equipped agent.
Add the package
Point it at your vault
Start the MCP server
Wire up your client
Then tell your agent: always check memory before asking the user to repeat themselves.
Frequently asked questions.
Short answers to the questions developers ask most about Genesys.
What is Genesys under the hood?
Genesys is an open-source AI agent memory engine from Astrix Labs. It combines a multiplicative scoring engine, a causal graph, and a lifecycle manager so the right memories surface, stale ones decay, and every recall can explain itself. It speaks MCP natively and is AGPLv3 licensed.
How does Genesys score memories?
Genesys scores each memory multiplicatively as relevance multiplied by connectivity multiplied by reactivation. Because the factors are multiplied rather than added, a zero in any single dimension drops the score to zero, so memories must earn recall across every dimension instead of coasting on one strong signal.
Does Genesys require API keys?
No. Genesys can run fully local by setting GENESYS_EMBEDDER=local, which uses an on-device embedder with no API keys required. Paired with the Obsidian vault backend, the entire memory pipeline runs on your own machine while leaving your existing vault files untouched.
How does Genesys score on LoCoMo?
Genesys scores 85.55 on the LoCoMo benchmark, certified over 10 runs under the strictest published protocol — ahead of every published alternative by more than ten points, with the next best around 75. We publish the methodology and our failure ledger alongside the number.