A Claude Code plugin for agent memory persistence. Memories survive across sessions, enabling agents to build on previous work instead of starting fresh.
/koi:standupRequires Bun.
In Claude Code:
/plugin marketplace add anortham/koi
/plugin install koi@koi
git clone https://github.com/anortham/koi.git
cd koi
bun install
claude mcp add koi /path/to/koi/src/index.ts
Memories are stored as markdown files with YAML frontmatter in a .memories/ folder within each project:
.memories/
└── 2026-02-04/
└── 134602_bdbc.md
A central registry at ~/.koi/registry.json enables cross-project queries via the scope: "global" option.
{
content: "## What I learned\n\nThe auth system uses JWT tokens stored in...",
tags: ["auth", "investigation"]
}
// Recent memories in current project
{}
// Search with query
{ query: "auth" }
// Filter by tags
{ tags: ["bug", "fix"] }
// Time-based filtering
{ since: "1d" } // last day
{ since: "1w" } // last week
{ since: "yesterday" }
// Cross-project search
{ scope: "global" }
// Combine filters
{ query: "database", tags: ["migration"], since: "1w", limit: 5 }
When installed as a plugin, use /koi:standup or ask "What did I work on yesterday?"
Koi includes hooks that fire automatically:
MIT
Admin access level
Server config contains admin-level keywords
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 anortham/koi --plugin koiMiller-powered development workflow with subagent-driven execution, inline review, and Miller-first codebase orientation.
Cross-client MCP memory with checkpoints, recall, briefs, and standups for AI-assisted development
Local SQLite-backed code intelligence, content search, and workspace freshness for coding agents. Requires Node.js on PATH (the plugin launcher is a Node script).
Code intelligence server: search, navigation, and refactoring across 34 languages
Composite workflows that orchestrate Julie (code intelligence), Sherpa (workflow guidance), and Goldfish (persistent memory) for powerful development patterns. Includes TDD Powerhouse, Bug Detective, Smart Session Start, and more.
Deterministic long-term memory for Claude Code: every prompt captured, role-scoped memories served each turn, memory that survives /clear and compaction, and a decision ledger that explains every keep, merge, and drop. Local only — no cloud, no keys.
Extended Second Brain that learns as you work in Claude Code
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
Universal memory runtime — ambient working-memory substrate for Claude Code. Memory is not a feature you invoke — it's the substrate the agent operates on.
Persistent memory for Claude Code — search, ingest, and context across sessions via a Synix knowledge server
Automatic semantic memory for Claude Code — remembers what you worked on across sessions