opencode-mem vs pro-workflow
OpenCode plugin giving coding agents persistent cross-session memory — local SQLite + vector search, automatic memory capture, user-profile learning, and a web UI. Nothing leaves your machine. — versus — One SQLite store under every Claude Code session: corrections become FTS5-searchable rules that auto-load, research grows persistent wikis, and 37 hook scripts add quality gates.
Same job on rival harnesses: a persistent local store under every coding-agent session. pro-workflow puts SQLite + FTS5 rules under Claude Code; opencode-mem puts SQLite + vector recall with auto-capture under OpenCode.
| opencode-mem | pro-workflow | |
|---|---|---|
| Stars | 1.1k | 2.6k |
| Forks | 113 | 253 |
| Language | TypeScript | JavaScript |
| License | — | — |
| Last activity | 5 days ago | 3 days ago |
| Topics | memory, coding | coding, memory |
| Curated connections | 2 | 4 |
opencode-mem — the curator's take
For OpenCode users tired of re-explaining their architecture every session: auto-capture summarizes each prompt's work via a background structured-output call that reuses your existing opencode provider auth, memories inject into the first chat message, and the `.opencode-mem-project` marker file solves multi-repo workspaces properly (directory-driven identity, not env vars). A real web UI at :4747 for browsing what it learned. NOT for Claude Code — this is OpenCode-specific; pro-workflow and claude-reflect are the equivalents on that side. Auto-capture needs a provider that speaks structured output, and the default local embedding model downloads on first use. Inspired by opencode-supermemory, but local-first.
pro-workflow — the curator's take
The most complete attack on Claude Code amnesia we've mapped: correct it once and the correction becomes a durable, searchable rule; research lands in wikis that persist and even grow via an auto-research loop; hooks add git/secret guards and cost tracking. After 50 sessions the compounding is real. Two cautions: NO license file at review time (all rights reserved by default — same gap as this author's other tools), and 34 skills + 37 hooks is a lot of surface — adopt the memory core first, audit the hooks before letting them gate your commits.