rusty-brain is a persistent memory system for AI coding agents. It captures observations from agent sessions and stores them locally so your agents remember context across conversations. Supported agents include Claude Code, OpenCode, GitHub Copilot CLI, OpenAI Codex CLI, and Google Gemini CLI — all sharing the same memory store.
Each supported agent is configured to send observations to rusty-brain at the end of every session. Memories are stored in .rusty-brain/mind.mv2 at your project root. Any configured agent can read and write to this shared store, so context learned in one agent is available to all others.
curl -sSf https://raw.githubusercontent.com/brianluby/rusty-brain/main/install.sh | sh
irm https://raw.githubusercontent.com/brianluby/rusty-brain/main/install.ps1 | iex
After installing the binary, configure rusty-brain for each agent you use.
/plugin marketplace add brianluby/rusty-brain
/plugin install rusty-brain@rusty-brain
rusty-brain install --project --agents opencode
rusty-brain install --project --agents copilot
rusty-brain install --project --agents codex
rusty-brain install --project --agents gemini
rusty-brain install --project
This auto-detects which supported agents are installed on your system and configures all of them in one step.
Use --global instead of --project to install configuration in user-level directories (e.g., ~/.config/) so rusty-brain is available across all your projects without per-project setup.
Search your memories:
rusty-brain find "authentication"
rusty-brain find "query" --limit 5 --type decision
Ask a question about stored context:
rusty-brain ask "why did we choose PostgreSQL over SQLite?"
View recent activity:
rusty-brain timeline
rusty-brain timeline --limit 20 --oldest-first
View memory statistics:
rusty-brain stats
All commands accept --json for structured output, which is useful for scripting or piping into other tools.
Memories are stored in .rusty-brain/mind.mv2 at your project root. Add this directory to your .gitignore to keep personal memory data out of version control:
echo '.rusty-brain/' >> .gitignore
If you have memories stored in an older location (.agent-brain/mind.mv2 or .claude/mind.mv2), rusty-brain detects these on startup and shows migration instructions.
See docs/developer.md for build instructions, crate layout, quality gates, and the spec-driven development workflow.
Apache-2.0
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub brianluby/rusty-brain-old --plugin rusty-brainPersistent, decision-grade memory for Claude Code: recall relevant prior decisions before work and capture durable ones after — via the rusty-brain MCP server plus strictly fail-open capture hooks. Requires the `rusty-brain` and `rusty-brain-hooks` binaries on PATH (cargo install / Homebrew / signed release).
Persistent memory for AI coding agents. Survives across sessions and compactions.
Universal memory runtime — cross-session cognitive memory for Claude Code. Remembers decisions, patterns, and context across coding sessions.
Multi-tiered memory and knowledge base with semantic search, auto-compaction, and built-in evaluation. Works across Claude Code, Copilot CLI, OpenCode, Cline, and Cursor.
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 41 MCP tools, 4 skills, real-time viewer.
Persistent memory for Claude Code — memories survive across sessions, projects, and machines
PowerMem intelligent memory for Claude Code: add, search, update, and delete memories with Ebbinghaus decay and multi-agent support.