By jholhewres
Persistent, local-first memory that survives across Claude Code sessions and other AI tools, with hybrid vector+BM25 search, categorized memory storage, and optional team sync. Includes installation diagnostics, memory statistics, and a 30-day recoverable delete.
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.
Load persistent cross-tool memory for the current project (identity, recent decisions, relevant entities)
Diagnose Anchored installation, MCP registration, and database health
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
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.
Contains inline bash commands via ! syntax
Contains inline bash commands via ! syntax
Persistent cross-tool memory for AI coding agents. Local-first, single binary, zero dependencies.
Anchored gives Claude Code, Cursor, OpenCode, Gemini CLI, Codex, VS Code Copilot, and other MCP-compatible tools one shared memory database on your machine.
anchored is both the CLI and MCP server.For team-shared project memory, the optional self-hosted/server side lives in anchored_oss. Local Anchored remains the source of truth and the hot retrieval path.
Anchored stores small durable memories, not raw chat dumps by default. The public categories stay intentionally simple:
| Category | Use for |
|---|---|
fact | Stable truths about a user, project, team, stack, API, or system. |
preference | Personal preferences, project conventions, or team rules. Preferences have user/project/team scope. |
decision | Architecture, tooling, naming, process, or product decisions. |
event | Time-bound events: deploys, meetings, incidents, releases. |
learning | Non-obvious lessons, gotchas, root causes, post-mortems. |
plan | Intent, backlog, next steps, TODOs. |
summary | Handoffs, recaps, precompact snapshots, daily/project summaries. |
Behind those categories, Anchored stores lifecycle metadata (memory_type, kind, scope, origin, importance, confidence, expires_at, context_tier, curation_status) so search, context injection, retention, curation, and remote sync make consistent decisions without making the MCP API harder for agents to use.
anchored_context returns identity, project stats, recent durable knowledge, and recent important session events under a tight budget..mdc, and DevClaw.From GitHub Releases:
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 creates ~/.anchored/ and downloads the local embedding model when needed (~470 MB).
The plugin is the easiest path because it installs MCP registration, slash commands, hooks, and the auto-trigger skill together:
/plugin marketplace add jholhewres/anchored
/plugin install anchored@anchored
Restart Claude Code after installation. Available slash commands include /anchored:context, /anchored:search, /anchored:save, /anchored:stats, /anchored:doctor, and /anchored:purge.
Running context-mode too? Anchored now ships its own PreToolUse routing — it steers Read/Grep/Glob/Bash/WebFetch and subagents toward memory and the sandbox tools, the same mechanism context-mode uses. Running both plugins means two routing blocks competing for the model's attention, and context-mode's redirects can shadow Anchored's. Uninstall context-mode for the cleanest behavior — Anchored covers both the memory and the context-window story on its own.
claude mcp add -s user anchored anchored
npx claudepluginhub jholhewres/anchored --plugin anchoredMulti-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 system for AI coding sessions — cross-tool memory sharing with 6-dimensional hybrid search
Curated persistent memory for Claude Code. Write gate prevents bloat — only behavior-changing facts get saved. Tiered architecture: daily logs, structured registers, and auto-loaded working memory.
Automatic memory recall for Claude Code - remembers context from past sessions
Nemp Memory — Cognitive memory layer for AI agents across every platform. Local-first, zero cloud, works with Claude, Codex, Cursor, and Windsurf.
OpenLTM — Long-Term Memory for AI coding agents: semantic search, context injection, session learning