通过MCP为编码代理提供开源跨代理内存层。兼容Cursor、Claude Code、Codex、Windsurf、Gemini CLI、GitHub Copilot、Kiro、OpenCode、Antigravity和Trae。
cross-agent-memory 开源项目推荐(21 个)
cross-agent-memory 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 21 个仓库Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.
Cross-agent memory for AI coding tools: one self-hostable knowledge graph shared by Claude Code, Codex, OpenCode, Cursor, and the agents you build.
Multi-agent memory governance demo using Caura + OpenClaw. Three agents (Sales, Legal, Admin) share one memory backend with hard fleet boundaries enforced at the query layer. Shows scoped writes, blocked recall, cross-fleet synthesis, and conflict detection.
MCP-native infrastructure for persistent AI agent memory with encrypted storage, semantic retrieval and cross-agent continuity.
⚡ Relic — One soul, many agents. Transfer personality and memory across AI agents via pure Markdown. Zero deps, human-readable. Switch agents, keep the soul.
Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.
One memory for all your AI agents. Local markdown files shared across Claude Code, Codex, Cursor, and any skills-compatible agent..
Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.
Portable, local-first AI agent memory and personal context—switch agents without losing identity, goals, rules, or evidence.
Hit your Codex limit mid-task? Open Cursor, say "continue from Codex", and keep going. ACM gives Codex, Claude Code, Cursor, and OpenCode one shared memory, so you never paste context again, and any agent can put the others to work.
💻 iTerm2 keyboard shortcut to fork the active coding agent CLI session into a new tab. Suports cross-agent session forking, e.g. codex <-> claude, claude <-> opencode, codex <-> opencode
AI screen memory for macOS. Capture your work as searchable Markdown notes and tasks. Let Codex and Claude Code recall saved context through a built-in MCP server.
A human-driven memory infrastructure for AI agents: shared context across agents, workspaces and teammates. Unified decisions, notes and session units as searchable .md cards, privately hosted and served over MCP to major agents like Claude Code, Codex, Cursor, Hermes and more.
Portable text block for giving structured context to AI agents — embed anywhere, parse anywhere
Local SQLite memory for LLM agents and cross-agent context sharing
该项目在 GitHub 上没有填写描述
Python SDK for Synapse Layer — persistent, encrypted, cross-agent memory for AI agents.
RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
Public shared persistent memory and coordination workspace for AI agents — cross-agent state, handoff, continuity and discovery.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/cross-agent-memory。
- 该话题在 GitHub 上共有 21 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1192 Star,覆盖 5 种主要语言,数据更新于 2026-11-10。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。