No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by jallum · Agent Tool · ★ 78
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is beadwork safe to install? View the security audit →
Beadwork Git-native work management for AI coding agents. Why AI coding agents lose context constantly — compaction, session boundaries, crashes. Plans they build in-context die silently. The agent picks up where it left off with no memory of what it decided or why. Beadwork gives agents durable state in git. Plans, progress, and decisions persist as files on a git branch. Nothing touches your working tree. Two agents working on the same repo never touch the same file. Sync is just git push. What It Looks Like You talk to your agent normally. Beadwork works behind the scenes. "Plan the auth module refactor" "What's next?" "Continue where we left off" "Use a team to do bw-xyz and bw-abc" Community Join the Beadwork Discord for discussion, support, and updates. Install Or download a binary from releases. To update an existing install: . Coming from beads? see docs/migration.md. Quick Start bash bw in
| Stars | 78 |
| Forks | 9 |
| Language | Go |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 73.4805572974174/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-14 |
| Created | 2026-02-19 |
| Platforms | go |
| Est. Tokens | ~16k |
Looking for a beadwork alternative? If you're comparing beadwork with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Autonomous Engineering
The universal skill manager for AI coding agents.
A memory layer for AI Agents
A simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities
A plugin with compound engineering workflows and memory for AI coding agents
Workspace-based coding environment for running multiple Claude Code and Codex sessions in parallel.
Explore other popular agent tool tools:
beadwork is Beadwork is a git-native work management tool for humans and AI coding agents. Plans, progress and decisions persist as files on an orphan-branch, not as cruft in yours.. It is categorized as a Agent Tool with 78 GitHub stars.
beadwork is primarily written in Go. It covers topics such as agents, coding, workflow.
You can find installation instructions and usage details in the beadwork GitHub repository at github.com/jallum/beadwork. The project has 78 stars and 9 forks, indicating an active community.
beadwork is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to beadwork on Agent Skills Hub include bosun, agent-skill-manager, remind. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: