Agent
Claude Code agents for Agent Memory
Flowy lists 66 subagents for Agent Memory, and the most-starred are beads-section, beads-section-codex and beads-section-minimal, all three from the 28,238-star beads plugin. That plugin was last pushed on October 27, 2026.
beads-section beads-section-codex Agentbeads-section-codex
Use Beads (`bd`) for durable task tracking in repositories that include it. Use the `beads` skill at…
@gastownhallInstall Agentbeads-section-minimal Agentbeads-section-minimal
This project uses **bd (beads)** for issue tracking. Run `bd prime` to see full workflow context and commands.
@gastownhallInstall Agentcontext-gatherer Agentcontext-gatherer
Gathers deep background from Supermemory before substantial work. Use when starting significant work in a repo, resuming after…
@supermemoryaiInstall Agentanalyzer Agentanalyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
@ecnu-icalkInstall Agentcomparator Agentgrader Agentinvestigator Agentinvestigator
Evidence-driven V3 investigation for current-state research, init bootstrap, and deep update passes.
@tokenrollaiInstall Agentrecorder Agentrecorder
Maintains stable V3 llmdoc knowledge and llmdoc/meta.json from CLI evidence plus scoped investigation.
@tokenrollaiInstall Agentreflector Agentreflector
Captures high-signal corrections, verified mistakes, and major rework as privacy-safe reflection candidates.
@tokenrollaiInstall Agentresearch-learner Agentresearch-learner
[Long-running, run synchronously] Use when user says: 'research X', 'learn about X', 'study X', 'build a knowledge tree for X',…
@mutable-state-incInstall Agentobserver Agentobserver
Background analyzer that runs on session start. Reads observations, creates instincts, detects clustering.
@humanplaneInstall Agentxurl-statusline-installer Agentxurl-statusline-instal…
Configure Claude Code statusLine.command for the xurl status line plugin.
@xuanwoInstall Agentcoderlm-subcall Agentcoderlm-subcall
You are a focused codebase exploration agent with access to a tree-sitter-indexed codebase. Your job is to answer a specific…
@jaredstewartInstall Agentbackend-dev Agentbackend-dev
后端开发工人。只在后端目录里开发，接口实现一律以 CONTRACT.md 指向的机器契约为准（只读，不许改），并为接口写"返回必须符合契约"的校验测试（provider verification）。可在单会话里被 contract-director…
@qshanxInstall Agentcontract-director Agentcontract-director
契约拥有者 / 集成对账者。唯一拥有并维护 CONTRACT.md（端与端的数据接口契约），先定契约，最后做集成对账。支持单会话多…
@qshanxInstall Agentdocs-auditor Agentdocs-auditor
Use this agent for read-only documentation audits. General requests such as 审计现有文档 or 检查文档治理漂移 use docs-audit; explicit…
@qshanxInstall Agentmemory-review Agentmemory-review
Review and curate memory suggestions from Engram's review queue
@joshuaswarrenInstall Agentgrowth-analyst Agentgrowth-analyst
Use this agent when the user wants to generate a growth report from Claude Code session data. This agent analyzes conversation…
@fivetakuInstall Agentauditor Agentauditor
Before you commit, publish, or trust something — a change, a claim, a plan, a "this is done."
@primefoldtoolsInstall Agentbuilder Agentchief-of-staff Agentchief-of-staff
You're scattered, stacked with options, or unsure what to do next.
@primefoldtoolsInstall Agentmemory-updater AgentENV AgentHEARTBEAT AgentIDENTITY AgentIDENTITY
- **名称**：小 R（XRK 工作区助手） - **角色**：办公协作 — 文档、邮件、纪要、调研摘要、任务拆解 - **语气**：清晰、礼貌、偏商务但不死板 - **签名**：回复末尾可不落款；用户要求时再署「小 R」
content-reviewer Agentcontent-reviewer
Review content for voice, guardrails, anti-AI patterns, and actionability.
@assafkipInstall Agentdata-ingest Agentdata-ingest
Pull calendar, email, Notion data. Structured extraction only, no analysis.
@assafkipInstall Agentengagement-hitlist Agentengagement-hitlist
Generate ranked, copy-paste-ready engagement actions from pipeline data.
@assafkipInstall Agentinstall_agent Agentinstall_agent
Agent with permissions to build and install Agent Brain locally
@spillwavesolutionsInstall Agentrelease_agent Agentrelease_agent
Agent with permissions to release Agent Brain packages. Handles version bumping, quality gates, building wheels, git tagging,…
@spillwavesolutionsInstall Agentresearch-assistant Agentresearch-assistant
Intelligent research agent that uses Agent Brain for knowledge retrieval with adaptive search modes
@spillwavesolutionsInstall Agentcode-explorer Agentcode-explorer
Explores indexed code structure using the OpenTrace knowledge graph. Finds classes, functions, files, directories, services,…
@opentraceInstall Agentdependency-analyzer Agentdependency-analyzer
Analyzes dependencies and blast radius for code changes. Maps what depends on a given component and what it depends on. Use this…
@opentraceInstall Agentexplain-service Agentexplain-service
Explains how a service, module, or major component works by walking the OpenTrace knowledge graph from the top down. Use this…
@opentraceInstall Agentresearcher-prompt Agentresearcher-prompt
You are a research specialist for codebase exploration and web research.
@kaimingwanInstall Agentreviewer-prompt Agentreviewer-prompt
You are a senior reviewer. Your job is to catch issues that would cause failure or wrong results — not to pursue perfection.
@kaimingwanInstall Agentreviewer Agentreviewer
Fresh-context reviewer of a change, on Sonnet at high effort, with no edit tools. Use ONE per change before it merges or ships.…
@maximocorrea1Install Agentscout Agentscout
Finder, on Sonnet at low effort, with no edit tools. Use when the answer needs many files, a long log, a CI run, vendor docs or a…
@maximocorrea1Install Agentworker Agentworker
Builder for ONE specified slice, on Sonnet at high effort. Use for a test-first implementation, a mechanical multi-file edit from…
@maximocorrea1Install Agentmanaged-section-full Agentmanaged-section-full
<!-- BEGIN BEADS INTEGRATION v:1 profile:full hash:bacef91e -->
@gastownhallInstall Agentmanaged-section-full-no-remote Agentmanaged-section-full-n…
<!-- BEGIN BEADS INTEGRATION v:1 profile:full hash:9c890b20 -->
@gastownhallInstall Agentmanaged-section-full-user Agentmanaged-section-full-u…
<!-- BEGIN BEADS INTEGRATION v:1 profile:full hash:0d9cad1f -->
@gastownhallInstall Agentdocs-governor Agentdocs-governor
项目文档 setup 编排与活文档治理执行者。首次配置新项目、讨论后项目或已有项目时，按共享 Skill 协调产品文档与 Agent 入口；维护期按需增量更新治理载体，不固定铺满四件套。
@qshanxInstall Agentfrontend-dev Agentfrontend-dev
前端开发工人。只在前端目录里开发，数据接口一律以 CONTRACT.md 指向的机器契约为准（只读，不许改）。可在单会话里被 contract-director…
@qshanxInstall Agentproduct-docs-manager Agentproduct-docs-manager
产品文档管理员。用户要求登记原始材料、整理产品认知与规划、维护需求池与单需求、关联版本及验收复盘，或统一需求编号、来源和生效基线时使用。复用已有产品资料和任务入口，不代替产品负责人批准需求。
@qshanxInstall Agentmemory-steward Agentmemory-steward
Your memory folder is growing, the index is getting long, or facts feel duplicated or stale.
@primefoldtoolsInstall Agent
Questions
What is the best Agent Memory subagent for Claude Code?
By the GitHub stars of the plugin each ships in (Flowy does not rate quality), the best Agent Memory subagent for Claude Code is beads-section, level on stars with beads-section-codex and beads-section-minimal, all three from the 28,238-star beads plugin.
How many Agent Memory subagents are there?
Flowy lists 66 subagents for Agent Memory, and this page draws the top 47 Agent Memory subagents and leaves out 1 documentation file the index read as subagents (HOW_TO_BUILD_AN_AGENT).
Agent Memory in other kinds
Other subagent categories
- Development5,722
- Agent Orchestration1,436
- AI & Agents809
- Automation687
- Security424
- Testing280
- Content233
- Marketing192
- Productivity191
- Monitoring143
- Writing128
- Product103
- Skill Authoring93
- Research91
- Design74
- Agent Workspaces72
- Data72
- Documentation61
- Mobile59
- Business57
- Operations54
- Finance47
- Machine Learning41
- Education39
- Cloud & Infrastructure38
- Legal29
- MCP Servers25
- Code Generation22
- Code Review21
- Spec-Driven Development18
- Databases16
- Backend11
- SEO10
- Video & Audio10
- Debugging9
- Deployment9
- Frontend9
- Career8
- Data Science6
- Presentations6
- Sales6