Back to directory

Beads

A distributed, graph-based issue tracker for AI coding agents, built on Dolt, that replaces markdown task lists with a dependency-aware graph agents can query and update.

Beads

Beads is a distributed graph issue tracker for AI coding agents, built on Dolt, a version-controlled SQL database with cell-level merge and native branching. It gives agents persistent, structured memory in place of markdown plans, using a dependency-aware graph so agents can handle long-horizon tasks without losing context.

An agent creates issues, sees which ones are ready and unblocked, claims and closes them, and dependent issues become ready once their blockers close; changes sync between machines and agents through Dolt remotes. Hash-based IDs avoid merge collisions in multi-agent and multi-branch workflows, JSON output and dependency tracking suit agent consumption, and older closed tasks are summarized to save context window. A messaging issue type supports threaded, temporary messages between agents.

It installs as a standalone CLI for macOS, Linux, Windows and FreeBSD, and can set up integrations for agents such as Codex, Claude Code and Cursor, writing an AGENTS.md file so agents discover the workflow. It is written in Go and licensed under the MIT license.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.