GiulioDER/RE-call

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 A superseded claim is marked superseded; a result that does not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 recallsearch 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.
mermaid
flowchart LR
subgraph groupentry["Entry points"]
nodecli["recall CLI commands"]
nodemcp["MCP server tool handlers"]
nodesdk["Agent SDK in process"]
end
subgraph groupbuild["Generation build"]
nodemanifest["Source manifest immutable input"]
nodegenerations["Generation manager build, validate, promote"]
nodeparser["Parse and chunk documents to chunks"]
nodeembedder["Embedder local or hosted API"]
nodegraphbuild["Semantic graph entities, relations"]
nodecalibration["Calibration certified threshold"]
end
subgraph groupserve["Trusted retrieval"]
nodetrustedsearch["Trusted search query orchestrator"]
nodegenstore["Generation store pinned generation"]
noderetriever["Hybrid retriever dense, full text, RRF"]
nodereranker["Reranker opt in"]
nodetrustgate{{"Trust gate verdict or ABSTAIN"}}
end
subgraph groupreason["Reasoning"]
nodereasoner["Reasoning query evidence bundle, plan"]
nodegraphexpansion["Graph expansion one hop, before trust"]
nodeanswer["Answer provider opt in LLM"]
end
subgraph groupfacts["Provenance and facts"]
nodeprovenance["Provenance controller fact review"]