AIAny
AI Agent2025
Icon for item

Beads

Provides a persistent, dependency-aware structured memory for coding agents — replacing scattered markdown plans with a versioned task/issue graph backed by Dolt. Agent-optimized features include JSON output, dependency tracking, zero-conflict IDs, and semantic compaction for long-horizon workflows.

Introduction

Long coding tasks and multi-agent workflows break when context lives in ephemeral notes or disconnected issue threads. Beads treats agent memory as a versioned, relational graph so state, dependencies, and audit history survive branching, merges, and agent churn — making long-horizon automation practical again.

What Sets It Apart
  • Dolt-backed, versioned memory: using Dolt gives true branching, cell-level merges, and history for structured agent state — so multiple agent runs can branch, experiment, and merge without losing provenance.
  • Agent-first data model: issues are structured records (JSON output, typed fields, dependency links) rather than freeform markdown, letting agents read/write programmatically and detect "ready" tasks automatically.
  • Zero-conflict and semantic compaction: hash-based IDs avoid merge collisions across agents/branches; older closed tasks can be summarized to reduce context size while preserving searchable history.
  • Git-free and multi-mode operation: works embedded (single-writer Dolt instance) or server-backed for concurrent writers, and supports a stealth/git-free mode for local or CI usage.
Who It's For and Tradeoffs

Great fit if you run autonomous or semi-autonomous coding agents, coordinate many short-lived agent actors, or need reproducible, auditable task state across branches and experiments. It helps teams turn planning notes into a machine-readable dependency graph that agents can act on.

Look elsewhere if you only need lightweight, human-only todo lists or a simple issue tracker — Beads adds operational complexity (Dolt concepts, branching workflows) that are overkill for small projects. Embedded mode is single-writer by design; use server mode for true concurrent writers and expect extra operational setup when enabling that.

Where It Fits

Beads sits between plain issue trackers and full RL/agent orchestration platforms: it focuses narrowly on durable, queryable agent memory and task graphs rather than scheduling compute or providing LLM runtimes. Use it to give agents a dependable memory layer that integrates with your repos, CI, or centralized Dolt remotes.

Information

  • Websitegithub.com
  • Authorsgastownhall
  • Published date2025/10/12

More Items

Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).