logo

gastownhall/beads

Beads - A memory upgrade for your coding agent

View on GitHub ↗Jump to charts ↓Open shareable report →

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 23 minutes ago
Type:CLI ToolCategory(s):AI Coding AgentsRAG, Knowledge & MemoryAI Agents & LLM Apps
Added to GitGenius on January 14th, 2026
Created on October 12th, 2025
Open Issues & Pull Requests: 1,402 (-2)
GitHub issues: Enabled
Number of forks: 1,878
Total Stargazers: 27,751 (+2)
Total Subscribers: 94 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 27.6 hours
Mean response time: 8.4 days
90th percentile: 27.5 days
Tracked items: 2,084

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

7 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 7, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits.

How this project is maintained

Roughly one issue in four opened in the past year never receives a reply. 82% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "bug" is answered fastest, typically in about 4 hours, while "kind/bug" waits about 10 days. Almost all tracked open issues have seen activity in the last three months. 64% of issues opened in the past year have been closed, leaving a working backlog.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1,014
New in 7 days: 95
Closed in 7 days: 19
Avg open age: 48 days
Stale 30+ days: 6
Stale 90+ days: 0

Recent activity

Opened in 7 days: 89
Closed in 7 days: 19
Comments in 7 days: 83
Events in 7 days: 341

Top labels

  • kind/bug (679)
  • priority/p2 (569)
  • priority/p1 (334)
  • triaged (245)
  • kind/chore (229)
  • priority/p3 (170)
  • kind/feature (166)
  • bug (67)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

Beads is a distributed graph issue tracker for AI coding agents that stores persistent, structured memory powered by Dolt.

The tool solves the problem of coding agents losing context during long-horizon tasks by replacing unstructured markdown plans with a dependency-aware graph database. It uses Dolt's version-controlled SQL backend to provide cell-level merge capabilities, native branching, and built-in sync. Tasks are tracked with hash-based IDs that prevent merge collisions in multi-agent workflows, and the system includes dependency tracking, semantic memory compaction to summarize closed tasks, and graph links like relates-to, duplicates, and supersedes. Agents interact through a CLI that outputs JSON and can discover the workflow via an AGENTS.md file.

Beads suits teams running multiple coding agents on shared projects who need coordinated task tracking without context loss. It works across macOS, Linux, Windows, and FreeBSD as a standalone CLI tool. The tool includes agent-specific setup for Claude, Codex, Factory, Mux, and Cursor, though manual integration is possible for unsupported agents. A stealth mode allows local-only usage without committing files to the main repository, and a contributor mode routes planning to a separate repository to keep experimental work out of pull requests. The README does not compare Beads to alternative approaches.

Almost all open issues are raised by outside users rather than the core team, indicating a substantial base of adopters reporting real-world use. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker is dominated by triaged, bug, and enhancement labels.