By b92c
Persistent cross-tool memory for AI coding agents. Single binary, zero dependencies, local-first. Shared between every IDE and AI tool you use.
Load persistent cross-tool memory for the current project (identity, recent decisions, relevant entities)
Diagnose Anchored installation, MCP registration, and database health
Wipe Anchored memory (default soft-delete; pass --hard for full DB reset with backup)
Save a memory to persistent cross-tool storage. Pass content as argument.
Search persistent memory (hybrid vector + BM25). Pass query as argument.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Runs pre-commands
Contains inline bash commands via ! syntax
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.
Persistent cross-tool memory for AI coding agents. Local-first, single binary, zero dependencies.
Anchored is a local-first MCP memory server that gives every AI coding agent and IDE you use a shared, persistent memory on your machine. Install once, and Claude Code, Cursor, OpenCode, Antigravity (agy), Gemini CLI, and any other MCP-compatible tool read, write, and search the same knowledge base.
No API keys. No daemon. All embeddings run locally.
For team-shared project memory, the planned self-hosted/open distribution lives in anchored_oss: organization-owned projects, team permissions, remote sync, privacy guardrails, and a future cloud-compatible protocol.
paraphrase-multilingual-MiniLM-L12-v2 (50+ languages, PT-BR and EN parity)anchored_execute/anchored_execute_file run code in 11 languages with stdout-only capture, hardened env, FILE_PATH/FILE_CONTENT injectionanchored_fetch_and_index mirrors URLs to a local FTS5 store; sandbox keeps raw data out of contextuser/project/team scope metadata on preferences (defaults to user)RemoteKey (SHA-256) for cross-machine consistencysync_state tableinspect for full JSON details, export with filters (JSON/JSONL)docs/team-sync.md and the sibling anchored_oss repoFrom GitHub Releases:
# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/jholhewres/anchored/main/install/install.sh | bash
From source:
git clone https://github.com/jholhewres/anchored.git
cd anchored && make build
sudo cp bin/anchored /usr/local/bin/
First run auto-downloads the embedding model (~470MB) and creates ~/.anchored/.
The fastest path. Installs the MCP server, six /anchored:* slash commands, and an auto-trigger skill in one step:
/plugin marketplace add jholhewres/anchored
/plugin install anchored@anchored
Then restart Claude Code. From any project: /anchored:context, /anchored:search <query>, /anchored:save <content>, /anchored:stats, /anchored:doctor, /anchored:purge. The skill triggers anchored_* tools proactively when memory is relevant — no need to ask.
claude mcp add -s user anchored anchored
The -s user flag registers Anchored at user scope so it's available in every project. Without it, claude mcp add defaults to local. Entry lives at ~/.claude.json (not ~/.claude/mcp.json). Restart Claude Code to pick up the new server.
Run anchored init to auto-detect and register, or configure manually:
| Tool | Config file |
|---|---|
| Cursor | ~/.cursor/mcp.json |
| OpenCode | ~/.config/opencode/opencode.json |
| Gemini CLI | ~/.gemini/settings.json |
| Antigravity 2.0 | ~/.gemini/config/mcp_config.json |
| Antigravity CLI (agy) | ~/.gemini/antigravity-cli/mcp_config.json |
| VS Code Copilot | .vscode/mcp.json |
npx claudepluginhub b92c/anchored --plugin anchoredConsult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.