Ferrosa Memory
MCP-native memory server
A session ends and its context goes with it. The next one rebuilds the same understanding from scratch, at the same token cost, and arrives at a slightly different answer.
Ferrosa Memory is where that understanding lives instead — typed, bi-temporal, exportable, and open source, running next to your agent, as a shared service, or in a container.
Agents talk to Ferrosa Memory through a small set of MCP tools — ingest, retrieve, link, explain, and forget. The memory layer owns memory semantics: entities, folds, temporal facts, retrieval outcomes, intentions, skills, Datalog rules, and explanations.
Underneath, Ferrosa Database provides CQL storage, vector indexes, graph traversal, and durable S3-backed tiering. A background "dream cycle" consolidates new memories — discovering connections, scoring importance, and decaying stale recall — while you sleep.
Agents see a focused Tier 1 set of everyday tools by default. The full Tier 2 surface — batch operations, folds, bi-temporal facts, memo & plan tracking, skills, consolidation, and the Datalog governance plane — unlocks with include_all when an operator needs it.
Ingest and recall: ingest, search, find, edge, chunk & turn context, intention checks, the full session-task surface, feedback, stats, configure, and forget. Everything an agent reaches for in a normal session.
Batch ingest/edit, trajectory folds, bi-temporal facts, memo & plans, the intention lifecycle, stored skills, dream-cycle consolidation & graph inference, the Datalog expert system (rules, claims, approvals, explanations), and config/introspection.
Propose candidates, see the blast radius (edges, temporal chains, derived facts), then confirm a reversible retraction or a hard delete — all recorded in an append-only forget journal with crash recovery.
Source-aware relevance guards, lexical-overlap checks, authority/PageRank adjustments, and workspace filtering so hooks prefer silence over noisy context. Native full-text indexing speeds lexical recall.
First-class task state — focus stack, working set, and recovery hints — survives restarts and supports multi-agent handoff, so an interrupted agent can resume where it left off.
Session-start recall derives stable, workspace-specific sessions instead of leaking process-global state, and fallback recall stays semantic/procedural — never raw episodic transcript.
Vector stores answer “what looks similar?” That is a useful signal and a poor ranking. In Ferrosa Memory similarity is three of seventeen weighted channels — lexical BM25 and full-text carry exactly as much weight, alongside phonetic matching, graph authority, workspace affinity and recency.
| Capability | Ferrosa Memory | Vector store + RAG |
|---|---|---|
| Typed knowledge graph | Yes | No — similarity only |
| Bi-temporal fact history | Yes | Overwrite / append |
| Hybrid retrieval (lexical + vector + phonetic + graph) | Yes — RRF over 17 weighted channels | Vector (± keyword) |
| Explainable derived facts | Yes — Datalog | No |
| Auditable forgetting | Yes — blast radius + journal | Manual delete |
| Automatic consolidation | Yes — dream cycle | No |
| MCP-native tools | Yes | Framework-dependent |
Ferrosa Memory is product engineering, not a paper implementation — but the design draws on recent and classic work on agent memory, virtual context, graph retrieval, prompt compression, Datalog-style inference, and memory evaluation.
| Paper | arXiv | Theme |
|---|---|---|
| LoCoMo: Evaluating Very Long-Term Conversational Memory of LLM Agents | 2402.17753 | long-term conversational memory |
| LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory | 2410.10813 | memory evaluation |
| Memory in Large Language Models: Mechanisms, Evaluation and Evolution | 2509.18868 | memory taxonomy |
| Episodic Memory is the Missing Piece for Long-Term LLM Agents | 2502.06975 | episodic memory |
| Microstructures and Accuracy of Graph Recall by Large Language Models | 2402.11821 | graph recall |
| From Local to Global: A Graph RAG Approach to Query-Focused Summarization | 2404.16130 | GraphRAG |
| LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression | 2310.06839 | long-context compression |
| InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory | 2402.04617 | context memory |
Start local, inspect memory in the workbench, and watch raw context become linked, durable, queryable memory. Self-hosted today — from a single workgroup machine to a replicated cluster on the distributed Ferrosa store. A managed service is on the roadmap.