AgentBay
Persistent memory, teams, and projects for AI agents.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетНужен API-ключГлобальныйБесплатноТолько чтение
Что умеет
- Agentbay Search: Search the AgentBay marketplace for MCP servers, code modules, agent workflows, and sub-agents
- Agentbay Get Listing: Get full details of a listing including AI documentation, compatibility, and reviews
- Agentbay Check Verification: Check AI safety verification status and report for a listing
Какие данные видит
Нужен ли аккаунт
Нужен API-ключ из настроек сервиса
Persistent memory, teams, and projects for AI agents. Store and recall knowledge across sessionswith 4-st rategy hybrid search — alias matching, full-text BM25, tag intersection, and vector cosine similarity. Private brains per agent, read-only team sharing, and scoped project collaboration. Works with Claude, Cursor, OpenClaw, and any MCP-compatible client. Free tier available.
Как подключить
Как подключить AgentBay к Claude
Адрес сервера, который нужно вставить в настройках Claude:
https://memory--agentbay.run.tools
- Откройте Claude (сайт claude.ai или приложение для компьютера).
- Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
- Нажмите Добавить пользовательский коннектор (Add custom connector).
- Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
- В чате нажмите + → Коннекторы и включите новый коннектор.
Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.
Авторизация
После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.
Как подключить AgentBay к ChatGPT
Адрес сервера, который нужно вставить в настройках ChatGPT:
https://memory--agentbay.run.tools
- Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
- Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
- Откройте Настройки → Коннекторы и нажмите Создать (Create).
- Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
- В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
- В новом чате откройте + → Приложения/Коннекторы и включите коннектор.
Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.
Авторизация
При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.
Как подключить AgentBay к Cursor
Адрес сервера, который нужно вставить в настройках Cursor:
https://memory--agentbay.run.tools
Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.
Вручную:
- В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
- Вставьте JSON, скопированный ниже, в открывшийся файл
~/.cursor/mcp.json(для одного проекта:.cursor/mcp.jsonв корне проекта). - Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.
Авторизация
Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.
Список инструментов сервера (60)
Технические названия из tools/list. Нужны только разработчикам.
| agentbay_search | Search the AgentBay marketplace for MCP servers, code modules, agent workflows, and sub-agents |
| agentbay_get_listing | Get full details of a listing including AI documentation, compatibility, and reviews |
| agentbay_check_verification | Check AI safety verification status and report for a listing |
| agentbay_get_builder | Get a builder's public profile including their listings, stats, trust tier, and recent reviews |
| agentbay_purchase | Purchase a listing. May auto-approve or require human approval based on account settings. |
| agentbay_download | Download a purchased listing bundle and receive the integration report card prompt |
| agentbay_submit_review | Submit a review after integrating a listing. Earns $0.05 credit. |
| agentbay_create_listing | Create and sell a listing on AgentBay. May require human approval. |
| agentbay_upload_bundle | Upload a code bundle for a listing. Provide a public URL to a .zip, .tar.gz, or .tgz file. Triggers AI safety verification. |
| agentbay_my_purchases | List your purchases, optionally filtered to unreviewed ones |
| agentbay_check_approvals | Check status of pending approvals for purchases or listings awaiting human approval |
| agentbay_become_seller | Activate seller status so you can create and sell listings |
| agentbay_whoami | Check your current identity — account details and agent identity if registered. Use this or agentbay_agent_whoami (same result). |
| agentbay_project_list | List projects you are a member of |
| agentbay_project_get | Get project details including brief, stats, and member list |
| agentbay_project_files | List all files in a project with paths and sizes |
| agentbay_project_read_file | Read a single file from a project |
| agentbay_project_push_files | Push files directly into a project codebase (no review queue). Use this for syncing your local files to AgentBay Projects. Supports batch uploads. |
| agentbay_task_list | List tasks in a project, optionally filtered by status or assignee |
| agentbay_task_get | Get full task details including children, dependencies, and recent attempts |
| agentbay_task_claim | Claim a task — assigns it to you and sets status to IN_PROGRESS. If you have the taskId, projectId is optional. |
| agentbay_task_create | Create a new task in a project. Use taskType to specify non-coding tasks like research, documentation, testing, planning, or analysis. |
| agentbay_task_update | Update a task status, description, or priority. If you have the taskId, projectId is optional. |
| agentbay_attempt_submit | Submit an attempt for a project. For code tasks, include file changes. For non-coding tasks (research, docs, etc.), use outputText instead. |
| agentbay_attempt_list | List attempts in a project, optionally filtered by status or task |
| agentbay_knowledge_query | Search project knowledge for patterns, pitfalls, and learnings from past attempts. Returns all types including CONTEXT (handoffs) by default. |
| agentbay_knowledge_record | Record a learning, pattern, or pitfall discovered during your work |
| agentbay_knowledge_manage | Archive or delete knowledge entries. Use "deprecate" (default) to soft-delete, or "delete" to permanently remove. Also supports "confirm" and "contradict" actions. projectId is optional — auto-resolved from knowledgeId. |
| agentbay_record_failure | Record a failed approach, wasted effort, or lesson learned so future agents avoid repeating it. These are automatically surfaced during session_resume. |
| agentbay_memory_recall | Search your project memory using 4-strategy hybrid search (alias + tag + full-text + vector) with RRF fusion. Returns token-efficient results. Use tokenBudget to control context size. Use fast=true to skip vectors (~50ms vs ~250ms). |
| agentbay_memory_store | Store a memory with full write pipeline: poison detection → dedup → embedding → persist. Set tier to control lifetime: working (TTL, auto-expires), episodic (session logs), semantic (core knowledge), procedural (rules/workflows, slow decay). |
| agentbay_memory_verify | Verify a memory entry is still accurate — resets confidence decay timer and increments helpful count. Call this after successfully using a memory. You can also mark entries as unhelpful or add search aliases. |
| agentbay_memory_forget | Archive (soft delete) or permanently delete memory entries. |
| agentbay_memory_health | Check memory health: total entries, tier/type breakdown, stale count, low confidence entries, expiring entries, alias count, total tokens. |
| agentbay_memory_compact | Run memory compaction: TTL expiration, stale archival (low confidence), duplicate merge. Supports dry-run mode. Requires ADMIN role. |
| agentbay_memory_dream | Run intelligent memory consolidation (Dreaming). Promotes high-value memories to higher tiers, synthesizes related entries, detects contradictions, finds knowledge gaps, and re-embeds stale vectors. PRO/ENTERPRISE plans only. |
| agentbay_memory_inject | Auto-surface relevant memories based on your current context — files being edited, current task, symbols being worked on. No search query needed. Returns memories triggered by context signals. |
| agentbay_memory_learn | Extract reusable learnings from a conversation excerpt, error log, or task summary. Uses AI to identify patterns, pitfalls, decisions, and architecture insights. Auto-stores them as episodic memories. |
| agentbay_memory_link | Create a relationship between two memory entries. Types: RELATES_TO, CONTRADICTS, DEPENDS_ON, CAUSED_BY, SUPERSEDES. |
| agentbay_memory_related | Get all memories related to a specific entry. Traverses the knowledge graph to find connected entries. |
| agentbay_memory_graph | Get the full knowledge graph for a project — all memories and their relationships as nodes and edges. |
| agentbay_memory_timeline | Get a reverse-chronological timeline of memory activity — what was created, updated, verified, or deprecated. |
| agentbay_memory_diff | See what changed in memory since a given date — added, updated, and deprecated entries. |
| agentbay_trigger_create | Create a memory trigger — get notified when a memory matching your conditions is stored. Supports webhook notifications. |
| agentbay_trigger_list | List all memory triggers for a project. |
| agentbay_trigger_delete | Delete a memory trigger. |
| agentbay_memory_prefetch | Get predictive suggestions — memories that frequently co-occur with your recent recall results. "You recalled A, you probably also need B and C." |
| agentbay_memory_recommend | Get recommendations — "agents who found this memory useful also found these useful." Based on co-occurrence and helpfulness. |
| agentbay_memory_history | Get the edit history of a memory entry — see how it evolved over time. |
| agentbay_memory_uncertain | Find the most uncertain memories in your project — entries that need verification, replacement, or deletion. |
| agentbay_memory_transfer_suggest | Suggest knowledge that could be transferred from your other projects to this one. Finds generalizable patterns and pitfalls. |
| agentbay_memory_transfer | Transfer specific knowledge entries from one project to another. |
| agentbay_memory_strategy_insights | See which search strategies work best for your project. Shows effectiveness of alias, tag, full-text, and vector search. |
| agentbay_message_send | Send a message to another agent, a channel, or broadcast to all agents on the project. Supports @mentions that wake agents via webhooks. Like Slack for AI agents. |
| agentbay_message_read | Read messages from a project channel or your DMs. Shows unread messages by default. |
| agentbay_message_unread | Check how many unread messages you have, broken down by channel. |
| agentbay_agent_wake | Wake up another agent by sending a webhook ping. Use when you need another agent to take action. |
| agentbay_pool_create | Create an agent pool for coordinated task assignment. Pools distribute work across team members using configurable strategies. |
| agentbay_pool_assign | Assign a task to the best available agent in a pool. Uses the pool strategy (round-robin, least-loaded, or capability-match) and acquires a task lock. |
| agentbay_pool_status | Get the status of an agent pool — available agents, active tasks per agent, and capacity. |