# CPersona

> MCP memory server: persistent, searchable memory for Claude and any MCP
> host. Single local SQLite file, 3-layer hybrid retrieval (vector + FTS5 +
> keyword), zero LLM dependency — the server never calls a generative model.
> This site is the canonical documentation for the 2.5.x line; when another
> surface (README, bundled skill) disagrees, the site wins.

Key facts an agent should not guess wrong: recall responses are ordered
ascending by score (the LAST element is the best match); `store` dedup is
skip-not-upsert (changed content under a reused msg_id is NOT updated — use
update_memory); autocut is inert under the default rsf/rrf fusion modes
(set_recall_precision is the effective gate knob); profile rows carry no
score and can be cut by limit unless confidence scoring is enabled;
CPERSONA_MAX_MEMORIES is the vector scan window, not a storage cap.

## Docs

- [Getting Started](https://cloto-dev.github.io/CPersona/getting-started/): install, the embedding-server contract and its reference implementation, MCP client registration, verification
- [Architecture](https://cloto-dev.github.io/CPersona/architecture/): component layout, SQLite/FTS5 storage, the three retrieval channels and the fusion → gate → reverse pipeline, isolation axes, zero-LLM rationale
- [Tools](https://cloto-dev.github.io/CPersona/tools/): all 30 tools grouped by purpose, each linked to the contract it can surprise you with
- [Behavior Contracts](https://cloto-dev.github.io/CPersona/behavior-contracts/): the behaviors callers may rely on — recall ordering, confidence×fusion interaction, episode boundary penalty, scan window, dedup, autocut, profile scoring, gate_fallback, lock semantics
- [Operations Runbook](https://cloto-dev.github.io/CPersona/operations/): WAL-safe backup, degradation detection, recall tuning order, Japanese/CJK guidance, corpus indexing patterns, maintenance cadence
- [Configuration](https://cloto-dev.github.io/CPersona/configuration/): every environment variable with defaults; HTTP transport and its authentication requirements
- [FAQ](https://cloto-dev.github.io/CPersona/faq/): question-shaped index into the pages above
- [Quality Assurance](https://cloto-dev.github.io/CPersona/quality-assurance/): how a release is gated — audit rounds, the bug ledger, structural CI gates, mutation proof, and the gates that check the docs themselves

## Design

- [ACL / per-client capabilities](https://cloto-dev.github.io/CPersona/ACL_DESIGN/): named bearer tokens, per-agent read/write grants, deny-by-default
- [Degraded-mode advisory](https://cloto-dev.github.io/CPersona/DEGRADED_ADVISORY_DESIGN/): how recall reports a dead embedding layer instead of silently degrading
- [Operating context](https://cloto-dev.github.io/CPersona/OPERATING_CONTEXT_DESIGN/): distributing operator instructions to all connected MCP clients
- [Recall preview tier](https://cloto-dev.github.io/CPersona/RECALL_PREVIEW_TIER_DESIGN/): preview truncation and the get_contents expansion path
- [Release lifecycle](https://cloto-dev.github.io/CPersona/RELEASE_LIFECYCLE_STANDARD/): tier definitions (Stable / Current), pre-release ladder, support windows

## Optional

- [Repository](https://github.com/Cloto-dev/cpersona): source, README quick start, issues
- [PyPI](https://pypi.org/project/cpersona/): pip / uvx installation
- [Bundled agent skill](https://github.com/Cloto-dev/cpersona/tree/master/skills/cpersona-memory): teaches an MCP agent the store / recall / archive workflow and the CLAUDE.md policy block