Skip to content
opencode-memHome

Prerequisites

This plugin uses embedded Turso (@tursodatabase/database) with F32_BLOB vectors and exact cosine search via vector_distance_cos. No separate vector database or custom SQLite build is required.

Recommended runtime:

  • Bun
  • Standard OpenCode plugin environment
  • Internet access on first use if you use the default local embedding model, because the model is downloaded by @huggingface/transformers.
  • For source/development installs, run bun install before building or testing. The published plugin package installs its runtime dependencies automatically through OpenCode.

CI-tested platforms: Linux, Windows, and macOS 15 / macOS 26 on Apple Silicon (darwin/arm64). Intel Mac (darwin/x64) is not supported — @tursodatabase/database and fixed onnxruntime-node releases ship no x64 native binding. Older macOS releases are not excluded by that matrix; they are simply outside the current GitHub-hosted runner set.

Notes:

  • Vector embeddings are stored and searched directly in Turso; inserts store F32_BLOB vectors for exact cosine ranking.
  • Vector search uses exact cosine distance via vector_distance_cos (no DiskANN / approximate index), with optional keyword hybrid ranking when a query string is provided (@tursodatabase/database does not ship FTS5).
  • Session lookups use an indexed session_id column (backfilled from metadata.sessionID on schema v2).
  • Auto-capture and user profile learning require an AI provider that can return structured/tool-call output. Memory search/add/list still work without auto-capture provider configuration.

Hardware / resource expectations

Section titled “Hardware / resource expectations”

opencode-mem does not require a GPU. Local embeddings run on CPU via @huggingface/transformers and ONNX (there is no MLX backend). Extra VRAM is not needed.

Workload Typical extra resources
Local embeddings (default Xenova/nomic-embed-text-v1) About 0.5–2 GB RAM while the model is loaded, depending on the Hugging Face id you pick. First use downloads the model; disk cache lives under {storagePath}/.cache (default ~/.opencode-mem/data/.cache) and is often hundreds of MB to ~1–2 GB per model.
Remote embeddings (embeddingApiUrl + embeddingApiKey) Negligible local ML RAM — only plugin + Turso overhead.
Database / plugin Turso/libSQL on disk under storagePath. Size grows with how many memories you store, not with GPU memory.

Platform limits above still apply (no Intel Mac darwin/x64; use Apple Silicon, Linux, Windows, or a remote embedding endpoint). See Choosing / configuring embeddings.