Skill Detail

Give OpenCode project sessions persistent memory with opencode-mem

Add opencode-mem to OpenCode so coding sessions can store, search, and reuse project memories through a local SQLite and vector index.

Developer ToolsCustom Agents
Developer Tools Custom Agents Security Reviewed
⭐ 1k GitHub stars ⬇ 12.1k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill give-opencode-project-sessions-persistent-memory-with-opencode-mem Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
OpenCode, opencode-mem plugin, Bun or standard OpenCode plugin runtime
Install & setup
Add opencode-mem to the plugin list in ~/.config/opencode/opencode.json, restart OpenCode so the plugin installs, then configure ~/.config/opencode/opencode-mem.jsonc for storage, embedding, and memory scope settings.
Author
tickernelz
Publisher
Individual
Last updated
Jul 1, 2026
Quick brief

Use opencode-mem when an OpenCode operator needs project-specific and cross-project memory to survive across coding sessions. The agent adds the plugin to the OpenCode configuration, stores important project facts or decisions, searches prior memories during later prompts, manages scopes such as project or all-projects, and optionally reviews memories through the local web interface. Invoke this instead of using OpenCode normally when repeated sessions keep losing architecture decisions, user preferences, or project conventions that should be retrieved locally. The boundary is OpenCode persistent memory with local SQLite/vector search and memory tools inside a coding-agent workflow, not a generic vector database, standalone RAG platform, or broad agent-memory framework.

How it works

What this skill actually does

Inputs and prerequisites: OpenCode, opencode-mem plugin, Bun or standard OpenCode plugin runtime.

Setup notes: Add opencode-mem to the plugin list in ~/.config/opencode/opencode.json, restart OpenCode so the plugin installs, then configure ~/.config/opencode/opencode-mem.jsonc for storage, embedding, and memory scope settings.

Source and verification boundary: use https://github.com/tickernelz/opencode-mem as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Custom Agents workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.