“agent memory”

Persistent, versioned memory via the memstated daemon.

在当前微信会话中新增长期记忆。当好友或群成员明确说‘记住……’‘帮我记一下……’‘把这个存进记忆’或‘新增记忆’时使用

Run the OpenAI Codex CLI non-interactively as a child agent and get back its final reply plus a session id, with the prompt supplied as arguments, a file, or…

Search and retrieve information from the Appie brain — daily logs, project notes, decisions, topics, and long-term memory files stored in ~/.hermes/memory/.

Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story…

Manual-only usage collector for one finished agent launch or the whole current session (working time, exact runtime tokens, cache read/write, steps, and…

Local-first RAG memory system for AI agents.

Configure and extend the Pi coding agent: extension API (terminal-title spinner, status), global settings.json, models.json provider overrides, and…

Review Pi or Codex histories for reusable knowledge or recurring patterns where agents needed correction or excess steering.

Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history…

Audit and clean agent-facing Markdown in the current project.

Run Cursor Agent CLI as an independent coding agent for implementation, investigation, planning, or review in a local workspace.

Complete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tests.

Captures learnings, errors, corrections, and feature requests to enable continuous improvement.

Design and run Claude Code agent teams: parallel teammates with a shared task list who message and challenge each other.

Work with BIT lectures on Yanhekt (延河课堂, aita.yanhekt.cn) together with the AutoSlides app - fetch lecture recordings and slides, read the platform's fast…

Run the Claude Code CLI non-interactively as a child agent and get back its final reply plus a session id, with the prompt supplied as arguments, a file, or…

Universal AI Agent Telemetry, Token Waste Auditing, Buggy Code Diagnostics, and Autonomous Self Improvement Loop.

Create, update or audit a project's AGENTS.md so that any AI tool works from the same, verified conventions: what the project is, where its architecture is…

Models as actors: a language model as an actor the study's steps ask along message flows, prompts kept as data, and the runner that plays a model's pool.

Deep production-grade Playwright QA automation skill stack for strict POM architecture, no-static-wait synchronization, locator contracts, environment/prod…

Master context engineering for AI agent systems.

Use when | Gestión del conocimiento y memoria del usuario.

MemOS 记忆系统集成 - 持久化记忆存储与检索。使用场景：(1) 存储用户对话和偏好到云端记忆库 (2) 搜索召回相关记忆片段 (3) 需要跨会话记忆能力时。关键词：记忆、memory、记住、回忆、偏好、memos、memos