claude-smart

Quick Start

Claude Code

npx claude-smart install

Then restart Claude Code.

Requires Node.js (for npx) to already exist.

Alternatively, install via Claude Code's plugin marketplace:

claude plugin marketplace add ReflexioAI/claude-smart
claude plugin install claude-smart@reflexioai

To uninstall:

npx claude-smart uninstall

Or, if installed via the plugin marketplace:

claude plugin uninstall claude-smart@reflexioai

Codex

npx claude-smart install --host codex

Then fully quit and reopen Codex so hooks reload.

Requires the codex CLI on PATH and Node.js (for npx).

To uninstall:

npx claude-smart uninstall --host codex

Restart Codex after uninstalling. The uninstaller stops local claude-smart services and removes plugin/cache/config state; learned data under ~/.reflexio/ and ~/.claude-smart/ is preserved and shared with Claude Code, so you can switch between hosts without losing skills or preferences.

OpenCode

npx claude-smart install --host opencode

Then restart OpenCode in your project so it loads the plugin from opencode.json, the documented project config file. If that project does not already have a root config but does have .opencode/opencode.json or .opencode/opencode.jsonc, the installer updates that existing file instead of creating a second config. If both locations exist, the root config wins. Use --global to install into ~/.config/opencode/opencode.json for all OpenCode projects on this machine. The installer copies the active package to ~/.claude-smart/opencode/claude-smart, prepares that runtime immediately, and writes a file:// plugin entry so OpenCode reloads the same prepared package after restart.

OpenCode support is new and uses OpenCode's plugin loader to inject relevant learned context before each model request. Learning extraction runs opencode run --pure from an isolated temp project, so it uses OpenCode's default model unless you set CLAUDE_SMART_OPENCODE_MODEL=provider/model. Set that env var if your normal project config pins a different provider or model.

To uninstall:

npx claude-smart uninstall --host opencode

Restart OpenCode after uninstalling. The uninstaller removes the claude-smart entry from OpenCode's plugin list and deletes the copied OpenCode package; learned data under ~/.reflexio/ and ~/.claude-smart/ is preserved and shared across hosts.

Developing the plugin itself? See DEVELOPER.md for what the installer does, manual toggles via /plugins, and clone-based development.

Not supported: Claude Code Cowork, claude.ai/code web, or remote Codex environments without local plugin hooks — they run outside your local machine, so the local backend/dashboard and ~/.reflexio/ aren't reachable.

Why Learning, Not Memory

Most memory tools just record. Claude remembers what happened, but doesn't change what it does next.

claude-smart focuses on learning instead.

Four things this changes:

• 💡 Stop repeating the same mistakes: Produces actionable skills Claude can follow next time; memory only records what happened.

  Example: a deploy fails after Claude bumps prisma from 5.x to 6.0; you tell it to roll back because 6.0 breaks nested writes in your order flow. Memory: “deploy broke after prisma bump; user rolled back” Learning: “treat major-version bumps of ORMs/DB drivers as breaking — verify with integration tests, not just unit tests”

• 🚀 Start from the optimized path: Records and optimizes the steps that worked so Claude can reuse them, instead of re-exploring each session.

  Example: Claude spends several iterations trying to start the local dev environment before discovering that this repo requires pnpm dev:all instead of the usual npm run dev. Memory: “user mentioned that npm run dev did not work” Learning: “for this repo, always use pnpm dev:all to start the full local stack — npm run dev only starts the frontend and causes missing service errors”

  Instead of re-exploring, Claude Code starts from the proven path—reducing planning steps, latency, and token usage.

• 🌐 Project-specific and shared skills: Session memory disappears with the conversation. Project-specific skills preserve repo-local rules, while shared skills roll up patterns that should transfer across projects. Preferences stay scoped to the current project so per-repo preferences don't leak across projects.

• 🪶 Better context without prompt bloat: Distilled, deduplicated skills stay in dozens of tokens—not thousands—even as the project grows.

Demo

https://github.com/user-attachments/assets/ed84d73a-d5b7-4a0d-ab2c-f2c060c3f276

Key Features

• 🧠 Learn, don't just remember — Corrections become structured, deduplicated rules, not transcript replays.
• ⚡ Fully automatic learning — Every user turn, tool call, and assistant response is captured via lifecycle hooks and extracted into rules without you running anything.
• 📈 Continuously self-tuning, not just append-on-conflict — Existing rules are continuously refined, not just appended to. Wording gets clearer, when-to-apply triggers tighten or broaden as evidence accumulates, near-duplicates merge, stale rules are superseded, and dead ones are archived. The library gets sharper, not just bigger.

  e.g. correct the same npm test --run gotcha twice → consolidated into one rule. New evidence shows it applies to vitest too → scope broadened. Switch policy to pnpm test → old rule archived, new one supersedes it.

• 🔌 No external API call — semantic search runs on an in-process ONNX embedder (all-MiniLM-L6-v2), and all data (preferences, skills, interaction buffers) is stored locally on your machine (~/.reflexio/ and ~/.claude-smart/).
• 🔎 Hybrid search — Skills and preferences are indexed with vector + BM25 search for fast, robust retrieval.
• 🧪 Offline resilience — If the reflexio backend is down, hooks buffer to disk; the next successful publish drains them.
• 🧰 Manual correction marker — /claude-smart:learn in Claude Code, or bash ~/.reflexio/plugin-root/scripts/cli.sh learn in Codex, flags the last turn as a correction so the extractor weights it heavily.

Dashboard

A web UI for browsing session histories, inspecting preferences, and editing project-specific and shared skills. The dashboard auto-starts alongside the backend, so you can open http://localhost:3001 directly. Or run /claude-smart:dashboard in Claude Code to open it in your browser. In Codex, run bash ~/.reflexio/plugin-root/scripts/dashboard-open.sh.

How It Works

claude-smart builds three artifacts as you work and injects the relevant ones into Claude Code, Codex, or OpenCode:

• Preferences (project-scoped) — how you work in this specific repo (stack, role, small quirks). e.g. "uses pnpm, not npm"; "prefers terse answers"; "backend engineer — explain frontend with backend analogues."
• Project-specific skills — durable rules with triggers and rationales learned from corrections in a project. e.g. "always pass --run