@oh-my-pi/pi-mnemopi weekly downloads statistics

@oh-my-pi/pi-mnemopi

Local SQLite memory engine for omp agents.

This package is the Bun/TypeScript port of the Mnemosyne memory engine. It provides:

• Mnemopi, a small facade for remember/recall/stats/sleep workflows. • BeamMemory, the lower-level working/episodic memory engine. • MCP tool definitions and a dispatcher for host integrations. • Optional local ONNX embeddings through fastembed and optional OpenAI-compatible embedding/LLM endpoints.

The package does not bundle or download a local GGUF LLM. LLM paths are host-backend or OpenAI-compatible remote only; when no LLM is configured, deterministic heuristic paths are used.

Basic use

Lexical recall matches whole tokens, declared synonyms, underscore-separated identifier parts, and other forms of a word of at least four characters: the word plus s, es, d, ed, ing, er, ers, ment or ments, a final e replaced by ing/ion/ions, or a final y replaced by ies/ied. backup matches backups, facts matches fact and caching matches cache, but 1Password does not match pass or word, and redis does not match redistribution.

Configuration

Mnemopi accepts LLM and embedding options directly. MNEMOPI_* environment variables remain fallbacks/defaults when the matching constructor option is omitted.

Banks and host scoping

Mnemopi itself exposes banks directly through constructor options such as bank; it does not hard-code coding-agent project scoping.

The omp coding-agent wrapper adds mnemopi.scoping on top of those constructor options:

• global: one shared bank • per-project: isolated project memory • per-project-tagged: project-local writes plus global recall visibility

In per-project-tagged, the wrapper is responsible for combining project-local retention with global recall visibility. The package still just exposes banks plus constructor-level LLM and embedding options.

Common environment fallbacks:

• MNEMOPI_DATA_DIR / MNEMOPI_DB_PATH: default storage location. • MNEMOPI_DB_PAGE_SIZE: optional SQLite page size for new file-backed databases; use a valid power of two from 512 to 65536 or os to request the detected system page size. Unset preserves SQLite's default. • MNEMOPI_NO_EMBEDDINGS=1: force FTS-only recall. • MNEMOPI_EMBEDDING_MODEL: defaults to BAAI/bge-small-en-v1.5. • MNEMOPI_EMBEDDING_API_URL and MNEMOPI_EMBEDDING_API_KEY: OpenAI-compatible embedding endpoint. • MNEMOPI_LLM_ENABLED=1, MNEMOPI_LLM_BASE_URL, MNEMOPI_LLM_API_KEY, MNEMOPI_LLM_MODEL: OpenAI-compatible LLM endpoint.

Local embeddings use the fastembed npm package. Its default BGESmallENV15 model is 384-dimensional and uses the package's CLS pooling plus vector normalization path. Local GGUF LLMs are not available in this package.

Commands

Tests

Description from the npm listing.