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。
“Task memory” · 程式設計與開發 · AI 開發者工具·64 個結果
重新開始
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.

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.


Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.

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.


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.


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.


會學習你編碼品味的 AI 編程代理


Tavus is an AI platform for real-time conversational video agents it calls PALs, combining lifelike avatars, natural voice, memory, and API access for products and experiences.
Tavus is an AI platform for real-time conversational video agents it calls PALs, combining lifelike avatars, natural voice, memory, and API access for products and experiences.


Mastra is an open-source TypeScript framework for building, deploying, and observing AI agents and workflows. It gives JavaScript developers typed agents, durable workflows, memory, MCP tool support, and built-in observability so prototypes can scale into production.
Mastra is an open-source TypeScript framework for building, deploying, and observing AI agents and workflows. It gives JavaScript developers typed agents, durable workflows, memory, MCP tool support, and built-in observability so prototypes can scale into production.


Toolhouse is an AI worker platform that turns plain-language requests into finished work. You email or message an AI worker a task the way you would brief a colleague, and it plans the job, uses your connected tools — email, spreadsheets, CRM, Slack — and returns the deliverable to your inbox. It is model-agnostic, works with 5,000+ integrations, and offers an MCP server, a KPI dashboard and spend caps so teams can put agents to work with guardrails.
Toolhouse is an AI worker platform that turns plain-language requests into finished work. You email or message an AI worker a task the way you would brief a colleague, and it plans the job, uses your connected tools — email, spreadsheets, CRM, Slack — and returns the deliverable to your inbox. It is model-agnostic, works with 5,000+ integrations, and offers an MCP server, a KPI dashboard and spend caps so teams can put agents to work with guardrails.

Memoripy is an open-source memory layer that gives AI agents human-like short-term and long-term memory. It clusters concepts, applies memory decay, and retrieves only the most relevant context so chatbots and assistants respond without repeating themselves.
Memoripy is an open-source memory layer that gives AI agents human-like short-term and long-term memory. It clusters concepts, applies memory decay, and retrieves only the most relevant context so chatbots and assistants respond without repeating themselves.


Sim is the open-source AI workspace for building, deploying and governing AI agents. Create agents visually, in Chat or in code, ground them in a synced knowledge base, connect 270+ integrations, and control access, spend and deployment from one place — on Sim Cloud or self-hosted.
Sim is the open-source AI workspace for building, deploying and governing AI agents. Create agents visually, in Chat or in code, ground them in a synced knowledge base, connect 270+ integrations, and control access, spend and deployment from one place — on Sim Cloud or self-hosted.