Tag
Reduck 推出 MCP 记忆层,通过缓存和复用浏览器操作脚本,让 AI 代理的浏览器任务速度提升 2.5 倍,并内置 LinkedIn、Google Maps、Stripe 等常用网站的官方脚本库。
Reduck 推出 Reduck MCP,作为浏览器操作的记忆层,通过复用脚本让 AI 代理的浏览器任务提速约 2.5-3 倍,并借助 Chrome 扩展解决登录与反机器人检测问题,同时维护主流网站的官方脚本库。
Reduck MCP introduces a memory layer for browser agents that lets them write, store and reuse navigation scripts executed on the user's logged-in Chrome, making web browsing tasks 2-3x faster and cheaper than screenshot-driven Computer Use. A curated library of official scripts for sites like LinkedIn, Google Maps, Instagram and Stripe helps solve the cold-start problem.
The paper introduces Galahad, a memory layer for vLLM, SGLang, and llama.cpp that caches KV state and document text so repeated reads of the same tokens become a one-time cost, achieving byte-exact state restoration and dramatically better recall and energy use over stateless serving baselines and RAG.
Built a customer-support AI agent named SupportMemory using Hindsight for persistent memory to recall and retain customer context, improving personalization in interactions.
Valori is a deterministic memory layer designed for AI applications, aiming to provide reliable and consistent memory functionality.
Maximem Synap is a fast and accurate memory and context infrastructure for AI agents, achieving high benchmark scores (e.g., 92% on LongMemEval) with native support across 22 frameworks like LangChain.
Funes is a durable memory layer for coding agents that enables recall of past session traces, working locally and integrating with Hugging Face datasets.
The author describes building a memory layer for news-reading AI agents to handle deduplication and improve continuity across sessions, using SQLite and vector storage with a Python API, CLI, and MCP server.
This article highlights that benchmark scores for Engrava, a memory layer tool, can vary due to reader or judge stage variance even when retrieval results are unchanged, using LongMemEval results to illustrate the issue.
OMEM is a memory layer for AI agents that tracks beliefs over time, surfaces contradictions, and keeps provenance, aiming to replace static vector-store memory. The author is seeking early testers for this not-yet-production-ready tool.
Memoars is an invite-only encrypted memory layer that lets AI assistants share a unified memory via MCP, with client open-sourced and hosted coordinator coming soon.
Introduces mem0, an open-source AI agent memory layer that gives Claude and other coding agents persistent long-term memory, fixing the issue of starting fresh each chat session.
Mem0 is a persistent memory layer for AI agents, launched on Product Hunt to give agents long-term memory capabilities.
Verity is a new open-source, permission-aware memory layer for multi-tenant AI agents, preventing cross-tenant data leaks by enforcing access controls directly in retrieval queries rather than relying on model behavior.
Mem0 is an open-source memory layer that helps AI agents retain and retrieve user context across conversations using hybrid search (semantic, BM25, entity), with SDKs for Python and npm.
A technical blog post discussing the author's experience building a fully local AI memory layer, including what worked, what failed, and the design tradeoffs involved.
Kit For AI is a memory layer designed for AI agents, providing persistent context and knowledge storage.
A tweet shares a guide on a loop system used by a Google Senior AI PM for improving AI agents, featuring 4 stages, 5 engineering steps, and 147 GitHub commits as a memory layer with version control.
Second Brain is an open-source memory layer that lets Claude, ChatGPT, Cursor, and Codex share persistent, semantic searchable memory, deployed on Cloudflare Workers for user-controlled storage.