mem20 separates grounded facts from simulated scenarios at the storage layer — so your AI agents reason from evidence, not imagination. MCP-native, drop-in ready, no adapters.
Vector and BM25 indexes are grounded-only by construction. _add_to_vector_index() and _add_to_bm25_index() call _assert_grounded() on the lowest write path. Contamination is impossible regardless of which tool invoked the write.
Verified facts · source-anchored · established truth
Inferences · projections · hypothetical models
Today's AI agents hallucinate, confabulate, and forget — not because they're broken, but because their memory systems treat every stored token as equally real. mem20 fixes that by partitioning memory at the engine level:
Facts derived from real observations, user statements, or events. Indexed, searchable, and always attributable.
Hypotheticals, counterfactuals, and imagined scenarios — fenced off from recall indexes, never contaminating grounded truth.
Simulated records become grounded only when paired with real-world prediction resolution — not free-text self-assertion.
Run memory_audit_contamination() anytime. A clean system reports rate 0.0 — and the firewall makes that invariant structural.
Speaks Model Context Protocol over stdio. Drop into Hermes, Claude, Cursor, or any MCP host. 97 tools, 13 domains.
Blender and Unity ship as optional modules. Add Figma, Unreal, or anything else via the blank integration template.
| Layer | Component | Purpose |
|---|---|---|
| Transport | mcp/mcp_server.py | JSON-RPC 2.0 over stdio, tool dispatch |
| Cognition | cog/cognitive_engine.py | Plan, chain, reason, reflect |
| Memory | memory_engine/memory.py | Grounded vs simulated store, indexes |
| Governance | Store-level guards | Contamination firewall, epistemic veto |
curl http://localhost:8080/health → status check
curl http://localhost:8080/metrics → tool counters + contamination_rate
126 bots, isolated namespaces, cross-contamination rate 0%. Persistent per-bot memory that survives restarts and model swaps.
Working memory that persists across sessions. An agent that remembers what it was doing yesterday, last week, last month.
Run counterfactuals without polluting grounded recall. Promote simulations to facts only when evidence supports it.
Join the beta. Get early access, direct input on the roadmap, and a channel to the team building it.
Join the Beta →