Developer Preview Ferrosa Memory 0.23 — structured, linked, auditable memory for agentic systems.
Ferrosa Memory · 0.23 · Developer Preview

How Ferrosa Memory compares.

Most memory layers answer "what's similar?" Ferrosa Memory also answers "what changed, what's connected, why does this exist, and can I safely remove it?" Here's how that differs from Mem0, Zep/Graphiti, Letta, and the vector+RAG baseline — fairly, and grounded in each project's own docs.

See how it works Browse the tools

Capability comparison.

Each competitor cell is drawn from that project's own public documentation or repository. Where the docs don't clearly establish a capability, the cell is marked Unclear.

Capability Ferrosa Memory Mem0 Zep / Graphiti Letta Vector + RAG
MCP-native tools Yes21 tier-1 + 58 tier-2 tools Partialvia OpenMemory / mem0-mcp; OpenMemory deprecated YesGraphiti mcp_server MCP client onlyuses external MCP tools; no official Letta MCP server Partialsome vector-DB MCP servers; not inherent
Typed knowledge graph Yestyped entities + edges Partialentity linking; standalone graph store being deprecated Apr 2026 Yestyped entities / edges / episodes Partialvia pluggable graph backend; not core No
Bi-temporal facts (supersession history) Yestimestamped facts, supersession chain stays inspectable Nono validity-interval model documented Yest_valid/t_invalid + ingest timestamps; invalidate-not-delete Unclearno bi-temporal model documented No
Hybrid retrieval (lexical + vector + graph + recency) YesRRF over ~11 signals incl. PageRank Partialsemantic + BM25 + entity boost; no graph/recency fusion documented Partialsemantic + BM25 + graph traversal; recency via temporal metadata Partialtiered vector + recall search; no documented fusion Novector similarity, optional keyword
Explainable / derived facts (rules) YesDatalog-derived facts with proof trace Noextracted text, no rule engine Partialepisode provenance + temporal lineage; no logical rule engine Notransparent edits, no rule derivation Nosource-traceable chunks, no derivation
Forgetting w/ blast radius + reversible retraction Yesblast-radius preview + journal Partialdelete exists; no blast-radius / reversible audit documented Partialinvalidate-not-delete preserves history; no blast-radius UX documented Unclearblock / passage CRUD; no reversible-retraction feature documented Nodelete-by-ID only
Automatic consolidation Yesbackground "dream cycle" Partialadd-pipeline reconciliation / dedup; no consolidation cycle documented Partialincremental graph updates / invalidation; not a scheduled cycle Unclearagent-driven edits; no automatic consolidation documented Nomanual
Durable storage + tiering YesFerrosa DB backend, S3 tiering Partialvector / graph store; cloud-managed; no S3 tiering documented Partialgraph DB; cloud-managed; no S3 tiering documented PartialPostgres + pluggable stores; no S3 tiering documented Partialdepends on chosen DB
Self-hostable Yes Yeslibrary + self-hosted server YesGraphiti OSS; full Zep CE deprecated Apr 2025 Yes Yeswith OSS components
Managed cloud Nodeveloper preview / self-host Yesapp.mem0.ai YesZep Cloud YesLetta Cloud, app.letta.com Yese.g. Pinecone, managed Weaviate / Qdrant

Legend: Yes = documented / supported · No = documented absence · Partial = limited or indirect form · Unclear = public docs do not establish it.

Project by project

What each one is, and how Ferrosa Memory differs.

The agent-memory space is moving fast. These summaries reflect each project's current public posture, including notable 2025–2026 shifts — stated neutrally and factually.

🧩

Mem0

An open-source "memory layer" for AI agents that remembers user preferences and facts across sessions. An LLM extracts memories from conversations and stores them as embeddings with user / session / agent scoping, retrieved by a hybrid of semantic search, BM25 keyword matching, and entity linking. Ships as a Python / JS library, a self-hostable server, and a managed cloud (app.mem0.ai), under Apache-2.0.

How fmem differs: Mem0 centers on LLM-extracted free-form memories; Ferrosa Memory keeps a typed bi-temporal graph with rule-derived, explainable facts and auditable forgetting on a durable S3-tiered backend.

🕸️

Zep / Graphiti

Graphiti is an open-source temporal knowledge-graph engine (Apache-2.0) that is the core of Zep's commercial Context Graph platform. It ingests conversational and structured data into typed entity nodes, relationship edges, and episodes, and is explicitly bi-temporal: edges carry validity windows (t_valid / t_invalid) plus ingest timestamps, and conflicting facts are invalidated rather than deleted. Retrieval is hybrid — embeddings + BM25 + graph traversal.

How fmem differs: Zep/Graphiti is the closest match on the typed bi-temporal graph story. Ferrosa Memory adds a Datalog rule/derivation engine, a dream-cycle consolidation pass, and a blast-radius forgetting UX — none of which Graphiti documents as such.

🧠

Letta

An open-source framework (Apache-2.0) for building stateful agents that manage their own memory, descended from the Berkeley MemGPT "LLM-as-OS" work. Memory is organized into labeled in-context "memory blocks" across OS-inspired tiers — core memory (always in-context), archival memory (external vector / graph store), and recall memory (searchable history). The agent actively edits its own memory via tool calls. Available as OSS and as Letta Cloud.

How fmem differs: Letta centers on agent-driven self-editing memory blocks; Ferrosa Memory provides a typed graph, bi-temporal supersession, multi-signal fusion retrieval, and rule-based derivation as first-class server features rather than agent-managed state.

📚

Vector + RAG baseline

The default "roll-your-own" pattern (a category, not a product): store conversation or document chunks in a vector database — Pinecone, Weaviate, Qdrant, pgvector — and wire retrieval with a framework like LangChain or LlamaIndex, or simply lean on a long context window. Retrieval is vector similarity, optionally plus keyword or metadata filters; some frameworks add reranking. Both OSS components and managed clouds exist.

How fmem differs: the baseline answers "what's similar?"; Ferrosa Memory adds a typed graph, bi-temporal history, multi-signal RRF fusion, explainable derivation, automatic consolidation, and auditable forgetting beyond delete-by-ID.

Depth and correctness for teams comfortable self-hosting today.

Ferrosa Memory's differentiator is breadth and rigor in one self-hostable package: native MCP tooling, a typed bi-temporal graph, multi-signal RRF retrieval including PageRank, Datalog-derived explainable facts, dream-cycle consolidation, and reversible forgetting with blast radius — all on a durable S3-tiered Ferrosa DB backend. No single competitor combines all of these in one product today.

Mem0 and Letta both offer managed cloud platforms and large communities. Zep has a commercial offering and a peer-reviewed temporal-graph paper. The vector + RAG baseline wins on ubiquity and simplicity. Ferrosa Memory is self-host only, with no managed cloud yet.

The credible pitch is depth and correctness for teams that need explainable, auditable, temporally-correct memory and are comfortable self-hosting today.

Sources

Every claim is checkable.

Competitor capabilities above are grounded in each project's own public docs and repositories. The key vendor sources are linked here so the matrix can be verified independently.

Mem0: GitHub repo, Graph Memory / migration docs, OpenMemory, mem0-mcp, "What is AI Agent Memory".

Zep / Graphiti: Graphiti repo, "What Is a Temporal Knowledge Graph?", Zep paper (arXiv 2501.13956), CE deprecation announcement.

Letta: GitHub repo, MCP overview docs, archival memory docs, "Memory Blocks".

Vector + RAG components: Pinecone, Weaviate, Qdrant, pgvector, LangChain, and LlamaIndex — characterized at the category level from their respective public documentation.

See what the structure buys you.

Read how the typed graph, bi-temporal facts, hybrid retrieval, and auditable forgetting fit together — then browse the MCP tools your agents call.

How it works Browse the tools