SQLite + FTS5 memory store and 19 MCP-style tools for OpenContext Runtime
Project description
opencontext-memory
SQLite + FTS5 memory store and 19 MCP-style tools for OpenContext Runtime.
This package is the concrete memory backend the conductor (opencontext-sdd)
and the CLI (opencontext memory v2 …) read and write through. It is local
only — no network, no cloud sync, no third-party drivers — and rides the
Python 3.12 stdlib sqlite3 (FTS5 is built-in on the supported versions).
Public exports
from opencontext_memory import MemoryStore, WriteQueue
Storage shape
The canonical schema lives in
opencontext_memory/store/schema.sql
and is the single source of truth for tables, indices, and the FTS5 virtual
table. MemoryStore loads it on first open.
| Table | Role |
|---|---|
observations |
Canonical row store (id, sync_id, …, deleted_at) |
observations_fts |
FTS5 mirror of observations(title, content) |
memory_relations |
7-verb × 4-status typed relations |
sessions |
mem_session_start / mem_session_end |
Cross-process safety
Concurrent writers in the same process serialise through a per-connection
lock; concurrent writers across processes serialise through WriteQueue,
which uses fcntl.flock on POSIX and a msvcrt-compatible lockfile on
Windows.
Mock LLM
The package never makes network calls. The tests/conftest.py autouse
fixture asserts no real LLM env vars are set during test execution so future
tool surface inherits the same guarantee.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file opencontext_memory-0.1.0-py3-none-any.whl.
File metadata
- Download URL: opencontext_memory-0.1.0-py3-none-any.whl
- Upload date:
- Size: 53.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4d78d568243ace83a36a8b98c7b23ff5d8e269cfdb03d3b9e957707583d4a6d7
|
|
| MD5 |
b92f3f6326624fdb7379164a1dfd19d3
|
|
| BLAKE2b-256 |
888f78bc0568088ed80c2f19ba1dd1858547751ce6c11b7bdcdc10a149267bd2
|