Veracium MCP server

Veracium

<!-- mcp-name: io.github.veracium-ai/veracium -->

Veracium is a provenance-aware memory plug-in for agentic systems — durable, per-user memory that resists the injection and confabulation failures that plague naive agent memory. Provenance means every fact tracks who said it: a claim from an email your agent merely read can never become a "fact" it asserts. It remembers what the user said, past interactions, and what worked — and it remembers where each of those came from.

Veracium is the production distillation of an evaluation-driven research project (agent-memory): every design choice below traces to a measured finding, and the research's synthetic-corpus harness is reused as the regression suite.

Research: the evaluation instrument behind those findings — a longitudinal benchmark for agent memory — is described in Q. Spencer, "Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings" (arXiv:2607.21962, 2026).

Why it's shaped this way

relational edges (with unforgeable provenance); interaction history lives as dated episodes. A curated "wiki" view is compiled from them and cached — never the source of truth. (The layered design won on both short and 9-week horizons; flat stores each failed one regime.)

• Typed graph + dated episodes are the store of record. Entity facts live as

deadline) keep one current value with the prior value retained as history — "what did X used to be?" stays answerable. (The category commercial memory systems handle worst; Veracium's strongest.)

• Supersession, never erasure. Functional facts (preference, employer,

external docs) are quarantined structurally — stored as thirdpartyclaim edges with the claimant as subject, never as user facts. Content-type quarantine catches obligation/debt/renewal claims regardless of how plausible they look. (Held against a full plausibility ladder incl. contact-impersonation.) What this is, and is not: the store governs retention, retrieval, description and recommendation — what it will say and how it labels it. It does not instantiate, authorize or execute anything; those belong to the host's harness. Without an exclusive harness path that consumes the labels, Veracium's trust classes are advisory labelling, not enforcement.

• Representation is a security control. Third-party claims (received email,

calls a Complete callable you supply. A reference Anthropic provider ships in the box.

• Bring your own model. Veracium never owns your API keys or model choice; it

Neo4j/Postgres later via the Store interface.

• Embedded by default. Zero external services: one SQLite file. Swap in

Install

pip install "veracium[anthropic]"   # core + the reference LLM provider

Extras: [mcp] adds the MCP server, [dev] adds pytest. The core alone depends only on pydantic. To work from source instead:

git clone https://github.com/veracium-ai/Veracium.git && cd Veracium
pip install -e ".[anthropic,dev]"

Links: docs · veracium.ai · PyPI

Use (library)

from veracium import Memory, EvidenceAuthor, EvidenceContext
from veracium.llm.anthropic import AnthropicComplete

mem = Memory(llm=AnthropicComplete())   # or pass your own Complete callable

Shortened. The full README is on GitHub.