Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
beads
Beads - A memory upgrade for your coding agent
24.3kstars
1.6kforks
Go
agentsclaude-codecoding
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Beads enhances coding agents by providing structured memory to avoid repeating context in long conversations.
Use this when
- Your agent forgets past context mid-conversation
- You’re debugging a multi-file project with complex dependencies
- You need to reference earlier decisions without re-explaining
- You’re working with a large codebase and want to avoid re-uploading files
- Your agent keeps asking for the same information repeatedly
Don't use when
- You need real-time, unstructured chat without memory overhead
- Your agent handles stateless, single-turn interactions only
Capabilities
- Stores conversation history in a structured format
- Avoids re-uploading or re-explaining prior context
- Supports multi-file project memory
- Reduces token usage by summarizing past interactions
- Integrates with coding agents via simple API
- Preserves key decisions and rationale for later reference
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest gastownhall/beadsAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/beads curl -fsSL https://raw.githubusercontent.com/gastownhall/beads/main/SKILL.md -o ~/.claude/skills/beads/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
beads — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt