Skip to main content
Glama

⚑ The Problem

AI coding agents (Antigravity, Claude Code, Cursor, Windsurf) lose their memory between sessions. Every time you open a new conversation, clear context, or switch branches:

  • Architectural decisions are forgotten.

  • Past bugs and lessons are repeated.

  • Complex multi-step task graphs get lost.

Beads introduced versioned agent memory, but requires a heavy Go binary and an external Dolt SQL database daemon running in the background.

beadless gives your agents persistent, dependency-aware memory stored as plain JSON and Markdown committed directly into your repository.


Related MCP server: Projectmem

πŸ₯Š Beads vs. beadless

Feature

Beads

🧠 beadless

Runtime

Go binary daemon

Node.js / TypeScript Native

Storage Engine

Dolt SQL Database Daemon

Plain Git (JSON + Readable Markdown)

Installation

Heavy custom install / Dolt setup

npx beadless init (Zero-config)

Install Size

~150 MB+

< 3 MB

PR & Code Review

Hidden in Dolt binary storage

Clean, reviewable .beadless/ diffs

MCP Standard

Custom protocol wrappers

Native @modelcontextprotocol/sdk

Human Readable

Requires SQL queries

Auto-syncs MEMORIES.md & TASKS.md


πŸš€ 30-Second Quickstart

In your repository root:

npx beadless init

That's it! beadless will scaffold .beadless/ and automatically configure your Antigravity, Cursor (.cursor/mcp.json), or Claude Desktop environment.

πŸͺ Attach to Google Antigravity

Add to your Antigravity MCP settings (~/.gemini/antigravity/mcp_config.json):

{
  "mcpServers": {
    "beadless": {
      "command": "npx",
      "args": ["-y", "beadless", "mcp"]
    }
  }
}

πŸ€– Attach to Claude Code

claude mcp add beadless npx -y beadless mcp

πŸ’» Attach to Cursor / Windsurf

Add this to your MCP configuration (.cursor/mcp.json or settings):

{
  "mcpServers": {
    "beadless": {
      "command": "npx",
      "args": ["-y", "beadless", "mcp"]
    }
  }
}

πŸ› οΈ MCP Tools for Agents

When attached to an agent, beadless exposes these standard MCP tools:

  • beadless_global_recall: Cross-session & cross-workspace search! Queries all recorded chats, global memories, and past Antigravity conversation transcripts for past discussions, decisions, and fixes.

  • beadless_chat_save: Saves the current chat session's summary, decisions, and files touched into persistent isolated memory.

  • beadless_chat_list: Lists past recorded chat sessions across workspaces.

  • beadless_global_sync: Scans and indexes recent Antigravity transcripts into beadless global memory.

  • beadless_context: Dumps instant project briefing (tech stack, conventions, critical gotchas, and top unblocked tasks).

  • beadless_snapshot: Captures the current workspace state, modified/untracked files, and branch status into persistent memory.

  • beadless_remember: Records an architectural decision, lesson, or preference.

  • beadless_recall: Fuzzy-searches past decisions and gotchas in current project to avoid repeating mistakes.

  • beadless_delete: Removes a memory entry by ID or semantic description.

  • beadless_task_create: Adds a task with dependency tracking (blockedBy: ["task-1"]).

  • beadless_task_claim: Claims a task for the active agent session.

  • beadless_task_complete: Marks task complete and automatically unblocks downstream tasks.

  • beadless_task_list: Queries tasks (e.g. --ready for unblocked tasks only).


πŸ’» CLI Usage

You can also use beadless directly from your terminal:

🌐 Global Recall (Cross-Chat & Antigravity Intelligence)

# View overview of all recorded chats and Antigravity sessions
npx beadless global

# Search for any topic across all sessions, chats, and transcripts
npx beadless global "canvas font fix"
npx beadless global "gods-eye-view"
npx beadless global "auth overhaul"

πŸ’¬ Multi-Chat Isolation & Session Management

# Save current session accomplishments & decisions
npx beadless chat save "Implemented OAuth flow" \
  --summary "Switched to PKCE with argon2 session storage" \
  --decisions "Use httpOnly cookies" \
  --tags auth oauth

# List recorded chat sessions across projects
npx beadless chat list

# Show details of a specific chat session
npx beadless chat show <chatId>

# Auto-sync recent Antigravity transcripts into beadless global index
npx beadless chat sync

Remember a Decision

npx beadless remember "Use Argon2 for password hashing" \
  --category decision \
  --message "Argon2id is memory-hard and prevents ASIC/GPU attacks." \
  --tags auth security

Snapshot Workspace State (Auto-Recording)

# Capture immediate snapshot with automatic title and timestamp (keeps all old memories!)
npx beadless snap

# Custom snapshot title with description
npx beadless snap "Completed authentication and cookies"

πŸ—‘οΈ Delete / Forget Memories

# Interactive list of recent memories
npx beadless del

# Delete by exact ID
npx beadless del mem-1234

# Smart semantic deletion (understands what you mean and deletes matching memory)
npx beadless del "eski veritabanΔ± kararΔ±"

⏱️ Automatic Periodic Auto-Recorder (Watcher)

# Automatically records changes every 10 minutes (default)
npx beadless watch

# Custom interval (every 5 minutes, triggers on >= 2 modified files)
npx beadless auto --interval 5 --min-changes 2 --immediate

Recall Memories

npx beadless recall "password"

Manage Task Dependency Graph

# 1. Create root task
npx beadless tasks create "Design database schema" --priority high

# 2. Create dependent task (blocked by task-1)
npx beadless tasks create "Build authentication API" --blocked-by task-1

# 3. View task board
npx beadless tasks list

# 4. Complete root task (unblocks task-2)
npx beadless tasks done task-1 --outcome "Prisma schema created"

Instant Agent Bootstrap

# Dump formatted project context to terminal or clipboard
npx beadless context

πŸ“‚ Repository Layout

Everything is stored inside your repository under .beadless/:

your-repo/
β”œβ”€β”€ .beadless/
β”‚   β”œβ”€β”€ config.json         # beadless settings (auto-commit, prefix)
β”‚   β”œβ”€β”€ memories.json       # Structured decisions, lessons, context
β”‚   β”œβ”€β”€ MEMORIES.md         # Auto-generated human-readable memory log
β”‚   β”œβ”€β”€ tasks.json          # Dependency graph (blockedBy, claimedBy)
β”‚   β”œβ”€β”€ TASKS.md            # Auto-generated markdown task board
β”‚   └── context.json        # Stack, conventions & non-negotiables

Because it lives in git:

  • Branch-aware: Branches keep their own context or inherit from main.

  • Team-shared: Every git pull updates your local agent's memory.

  • Reviewable: You can see every AI agent decision in standard GitHub pull requests!


πŸ“œ License

MIT Β© KuraPiee β€” Built with ❀️ by the Docwyrm Team.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides persistent memory for AI coding assistants, storing and retrieving architectural decisions, patterns, and solutions across sessions using semantic search, while also offering git integration for commit messages and code expertise mapping.
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Local-first memory layer for AI coding agents β€” captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.
    17
    330 PyPI
    846
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Shared, code-grounded memory for developers and their coding agents. Capture a learning once and the whole team plus every agent recalls it; memory is grounded in your code and stored as git-tracked JSON reviewed in PRs, with citations validated on write and stale memory withheld from recall. Works with any MCP client.
    11
    33
    GPL 3.0
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to store, query, and update persistent project knowledge as a local, Git-friendly knowledge graph, providing structured memory across sessions.
    9
    Apache 2.0