#196196th of 389 in Skills, plugins and prompts
opencode-mem
Persistent vector-backed memory plugin for OpenCode coding agent sessions
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.9k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
486 on 21 Apr 20261,854 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenCode plugin that captures project memories when a session goes idle, stores them in an embedded Turso/libSQL database with exact cosine vector search, and injects relevant ones into later sessions. It also learns a cross-project user profile and ships a web UI at 127.0.0.1:4747 for browsing memories, skills and stats. Embeddings run locally on CPU or through an OpenAI-compatible API.
Who it is for: OpenCode users who want long-term memory across coding sessions
Strengths
- Embedded Turso/libSQL storage, so no separate vector database to run
- Local CPU embeddings with 12+ models, or any OpenAI-compatible embeddings API
- Redacts recognizable credentials and honors <private> tags before auto-capture
- Optional AES-256-GCM encryption at rest and Markdown vault export/import
Weaknesses
- Intel Mac (darwin/x64) is not supported
- On Windows only one OpenCode session can own the memory databases
- Auto-capture needs a provider that returns structured or tool-call output
- Credential redaction is partial and does not scan existing stored memories
What it needs
- RAM ≥ 0.5 GB
- no GPU
- Needs OpenCode, Bun, @tursodatabase/database, @huggingface/transformers
- Models: Xenova/nomic-embed-text-v1, OpenAI Chat Completions, OpenAI Responses, Anthropic, MiniMax
- port 4747
Quick answers
Is opencode-mem open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |