RE-call MCP Memory Server

Memory that abstains instead of guessing.

RE-call is agent memory in a local SQLite file or your own PostgreSQL with pgvector. Each result carries a verdict, confidence, and provenance, while unsupported questions are refused instead of answered by the nearest match.

What it is · For agents · How it works · Start with Lite · Install and integrate

What is RE-call

RE-call is agent memory in a local SQLite file or your own PostgreSQL database. It indexes source documents and keeps validity, lineage, confidence, and provenance attached to every result.

Vector search returns nearby text. RE-call also checks whether that text is current, supported, and trustworthy enough for the query. A superseded claim is marked superseded; a result that does not clear the calibrated trust gate becomes ABSTAIN with a reason. Declared supersession makes the current memory win over stale but similar memory.

The default path uses local embeddings plus hybrid dense and keyword retrieval. PostgreSQL uses its full text search; Lite uses SQLite FTS5. It needs no memory-layer LLM call. Additional retrieval, reasoning, and structured-fact modules are optional.

For the agent reading this, RE-call for agents explains the experience loop and how to use persistent memory as a trustworthy past rather than an unverified scratchpad.

How it works

On PostgreSQL, RE-call builds an immutable, calibrated generation and serves queries against that pinned generation. Lite binds calibration to its single-file corpus. Every search, including the reasoning and fact paths, goes through trusted search and the trust gate.

The diagram is interactive on the project site: click any box to see the source lines it describes. A step by step view of one recall_search call follows a single search through its refusal, abstention and answer paths. Both are generated from the sources in docs/diagrams.

Text version of the diagram, with each box linked to its file

Solid arrows are the default path. Dashed arrows are opt in or reasoning only: the reranker, graph expansion, and the answer provider. Each box links to the file that implements it.

flowchart LR

subgraph group_entry["Entry points"] node_cli["recall CLI commands"] node_mcp["MCP server tool handlers"] node_sdk["Agent SDK in process"] end

subgraph group_build["Generation build"] node_manifest["Source manifest immutable input"] node_generations["Generation manager build, validate, promote"] node_parser["Parse and chunk documents to chunks"] node_embedder["Embedder local or hosted API"] node_graph_build["Semantic graph entities, relations"] node_calibration["Calibration certified threshold"] end

subgraph group_serve["Trusted retrieval"] node_trusted_search["Trusted search query orchestrator"] node_gen_store["Generation store pinned generation"] node_retriever["Hybrid retriever dense, full text, RRF"] node_reranker["Reranker opt in"] node_trust_gate{{"Trust gate verdict or ABSTAIN"}} end

subgraph group_reason["Reasoning"] node_reasoner["Reasoning query evidence bundle, plan"] node_graph_expansion["Graph expansion one hop, before trust"] node_answer["Answer provider opt in LLM"] end

subgraph group_facts["Provenance and facts"] node_provenance["Provenance controller fact review"] node_ledger["Fact ledger append only"] end

node_caller(("Agent or user caller")) node_postgres[("PostgreSQL + pgvector generations, chunks, graph")]

node_caller -->|"runs"| node_cli node_caller -->|"tool calls"| node_mcp node_caller -->|"imports"| node_sdk node_sdk -->|"reuses handlers"| node_mcp node_cli -->|"generation build"| node_generations node_mcp -->|"ingest uploads"| node_generations node_generations -->|"reads sources"| node_manifest node_generations -->|"parses, chunks"| node_parser node_generations -->|"embeds chunks"| node_embedder node_generations -->|"builds graph"| node_graph_build node_generations -->|"requires certified"| node_calibration node_generations -->|"writes generation"| node_postgres node_graph_build -->|"writes graph"| node_postgres node_cli -->|"calibrate, publish"| node_calibration node_calibration -->|"stores threshold"| node_postgres node_cli -->|"search"| node_trusted_search node_mcp -->|"search, evidence"| node_trusted_search node_trusted_search -->|"pins generation"| node_gen_store node_gen_store -->|"reads active"| node_postgres node_trusted_search -->|"retrieves"| node_retriever node_retriever -->|"embeds query"| node_embedder node_retriever -->|"dense, full text"| node_gen_store node_retriever -.->|"reorders"| node_reranker node_trusted_search -->|"evaluates"| node_trust_gate node_mcp -->|"reasoning query"| node_reasoner node_reasoner -->|"retrieves"| node_trusted_search node_trusted_search -.->|"expands pre trust"| node_graph_expansion node_graph_expansion -.->|"same generation graph"| node_postgres node_reasoner -.->|"cited answer"| node_answer node_mcp -->|"apply fact"| node_provenance node_provenance -->|"fresh search"| node_trusted_search node_provenance -->|"appends"| node_ledger node_ledger -->|"stores"| node_postgres

click node_cli "https://github.com/GiulioDER/RE-call/blob/master/recall/cli.py" click node_mcp "https://github.com/GiulioDER/RE-call/tree/master/recall_mcp" click node_sdk "https://github.com/GiulioDER/RE-call/blob/master/recall_agent/memory.py" click node_manifest "https://github.com/GiulioDER/RE-call/blob/master/recall/manifest.py" click node_generations "https://github.com/GiulioDER/RE-call/blob/master/recall/generations.py" click node_parser "https://github.com/GiulioDER/RE-call/blob/master/recall/document.py" click node_embedder "https://github.com/GiulioDER/RE-call/blob/master/recall/embeddings.py" click node_graph_build "https://github.com/GiulioDER/RE-call/blob/master/recall/semantic_graph/_build.py" click node_calibration "https://github.com/GiulioDER/RE-call/blob/master/recall/calibration_v2.py" click node_trusted_search "https://github.com/GiulioDER/RE-call/blob/master/recall/trust.py" click node_gen_store "https://github.com/GiulioDER/RE-call/blob/master/recall/generation_store.py" click node_retriever "https://github.com/GiulioDER/RE-call/blob/master/recall/retriever.py" click node_reranker "https://github.com/GiulioDER/RE-call/blob/master/recall/rerank.py" click node_trust_gate "https://github.com/GiulioDER/RE-call/blob/master/recall/trust.py" click node_reasoner "https://github.com/GiulioDER/RE-call/blob/master/recall/reasoning.py" click node_graph_expansion "https://github.com/GiulioDER/RE-call/blob/master/recall_mcp/graph_expansion.py" click node_answer "https://github.com/GiulioDER/RE-call/blob/master/recall/answer_provider.py" click node_provenance "https://github.com/GiulioDER/RE-call/blob/master/recall/provenance_controller.py" click node_ledger "https://github.com/GiulioDER/RE-call/blob/master/recall/fact_ledger.py" click node_postgres "https://github.com/GiulioDER/RE-call/tree/master/recall/migrations"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554 classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337 classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81 classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a class node_cli,node_mcp,node_sdk,node_caller toneBlue class node_manifest,node_generations,node_parser,node_embedder,node_graph_build,node_calibration,node_postgres toneAmber class node_trusted_search,node_gen_store,node_retriever,node_reranker,node_trust_gate toneMint class node_reasoner,node_graph_expansion,node_answer toneRose class node_provenance,node_ledger toneIndigo

Ordinary recall search follows the direct path. Explicit reasoning accepts graph_expansion: auto is the default and resolves to bounded one hop expansion for every nonempty query; off keeps direct retrieval only; one-hop forces the graph path. The CLI uses --graph-expansion auto|off|one-hop; the MCP tool uses graph_expansion="auto"|"off"|"one_hop". Graph neighbors are generation bound, direct candidates remain first, and expanded candidates must clear the same trust boundary before they can support a cited answer.

The opt in choices attach to different points in the system:

For details, see the architecture writeup, provenance controller, and API reference.

Quickstart

For one project's memory on your machine, start with RE-call Lite. It stores memory in .recall/memory.db, refreshes changed memos automatically, and needs no Docker or database server.

Install 0.15.0 or later: Lite ships in the PyPI wheel from 0.15.0; earlier wheels do not contain it. Follow the Lite installation guide to create an environment and install the package, then run this from your own project with an existing folder of notes:

recall