涵蓋 459 類工作流程,透過流量估算、產品功能與替代方案協助選擇。
“Persistent AI memory” · 程式設計與開發·81 個結果
重新開始
Honcho is an open-source memory layer for AI agents. It ingests messages, indexes them, and runs background reasoning so agents can recall who a user is, what happened before, and what to do next — across sessions, tools, and machines.

Vellum is a personal AI assistant that you own and customize. It runs locally on your machine or in Vellum Cloud, remembers your context over time, connects to your tools and takes real actions like email, calendar, research and file work, with model choice across OpenAI, Anthropic, Gemini or local open weights via Ollama.
Vellum is a personal AI assistant that you own and customize. It runs locally on your machine or in Vellum Cloud, remembers your context over time, connects to your tools and takes real actions like email, calendar, research and file work, with model choice across OpenAI, Anthropic, Gemini or local open weights via Ollama.

EverMemOS (also described as EverOS) by EverMind is a memory operating system for AI agents and applications. It adds persistent, self-evolving memory on top of stateless LLMs: agents store multimodal content, retrieve it through hybrid mRAG, distill repeated patterns into reusable Skills, and keep facts in sync over time.
EverMemOS (also described as EverOS) by EverMind is a memory operating system for AI agents and applications. It adds persistent, self-evolving memory on top of stateless LLMs: agents store multimodal content, retrieve it through hybrid mRAG, distill repeated patterns into reusable Skills, and keep facts in sync over time.



ProMind AI is a personalized AI assistant platform built around memory. You create assistants tailored to your work, such as content creation, software engineering, product management, or cloud architecture, and they recall your context across sessions so you spend less time repeating yourself. It combines chat, writing, coding help, image generation, PDF extraction, task management, and live information into a set of reusable assistants.
ProMind AI is a personalized AI assistant platform built around memory. You create assistants tailored to your work, such as content creation, software engineering, product management, or cloud architecture, and they recall your context across sessions so you spend less time repeating yourself. It combines chat, writing, coding help, image generation, PDF extraction, task management, and live information into a set of reusable assistants.


會學習你編碼品味的 AI 編程代理

Termo is a platform for running AI agents on their own virtual machines. Each agent keeps a semantic memory graph, can spawn sub-agents, install skills from a large registry, browse the web, execute Python, and run on a cron schedule you set in plain language — so work keeps happening while you are offline.
Termo is a platform for running AI agents on their own virtual machines. Each agent keeps a semantic memory graph, can spawn sub-agents, install skills from a large registry, browse the web, execute Python, and run on a cron schedule you set in plain language — so work keeps happening while you are offline.

Writing.io is an AI workspace that puts GPT, Claude, Gemini and Grok in one place alongside an AI-assisted document editor, your project files, and thousands of ready-made tasks and automations. It also offers AI courses and certifications, an API, and a partner programme.
Writing.io is an AI workspace that puts GPT, Claude, Gemini and Grok in one place alongside an AI-assisted document editor, your project files, and thousands of ready-made tasks and automations. It also offers AI courses and certifications, an API, and a partner programme.
Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.
Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.
讓 AI 代理永不休眠的持久化虛擬機。



Scalebrowser is a desktop browser platform built specifically for AI agents. It gives each agent its own isolated browser profile with a persistent identity, so automations can stay signed in between runs instead of starting from a blank session every time. Agents connect over MCP, Python and Node SDKs, a REST API or direct CDP, and every tool call is captured as a step with a result and a screenshot.
Scalebrowser is a desktop browser platform built specifically for AI agents. It gives each agent its own isolated browser profile with a persistent identity, so automations can stay signed in between runs instead of starting from a blank session every time. Agents connect over MCP, Python and Node SDKs, a REST API or direct CDP, and every tool call is captured as a step with a result and a screenshot.
Openclaw is an open-source framework for building AI automations that run on your own machine. Messages arrive from WhatsApp, Telegram, Discord, Slack, Signal, or iMessage through a unified router; a programmable workflow engine in TypeScript or YAML decides what happens next; and plugins extend it into 50+ services. It keeps persistent memory across sessions, can browse the web and fill forms, and can read and write files or run shell commands under sandboxing you control. Model choice is open — Anthropic, OpenAI, or fully local via Ollama — all released under the MIT licence.
Openclaw is an open-source framework for building AI automations that run on your own machine. Messages arrive from WhatsApp, Telegram, Discord, Slack, Signal, or iMessage through a unified router; a programmable workflow engine in TypeScript or YAML decides what happens next; and plugins extend it into 50+ services. It keeps persistent memory across sessions, can browse the web and fill forms, and can read and write files or run shell commands under sandboxing you control. Model choice is open — Anthropic, OpenAI, or fully local via Ollama — all released under the MIT licence.


Llongterm is a long-term memory layer for AI apps and agents. It sits between your chatbot and its memory, remembering users across conversations and storing everything in a fully human-readable format through a simple JavaScript API.

Raft (formerly Slock.ai) is an agent-native team workspace where humans and AI agents collaborate as teammates in shared channels, threads, and tasks, with each agent keeping its own memory on your machine.