CLI 界面
掌握 Ailiv Agent 终端界面——命令、快捷键、人格设定等
Egress proxy
1 个项目
配置
配置 Ailiv Agent — config.yaml、providers、模型、API 密钥等
Profiles:运行多个 Agent
在同一台机器上运行多个独立的 Ailiv agent——每个 agent 拥有各自的配置、API 密钥、记忆、会话、技能和 gateway 状态。
TUI
启动 Ailiv 的现代终端 UI——支持鼠标操作、丰富的浮层面板和非阻塞输入。
Windows (WSL2)
通过 WSL2 在 Windows 上运行 Ailiv Agent —— 安装配置、Windows 与 Linux 之间的文件系统访问、网络设置及常见问题
配置模型
Ailiv 使用两类模型槽位:
Ailiv Desktop
The native Ailiv desktop app — a polished experience for chatting with Ailiv, with streaming tool output, side-by-side previews, a file browser, voice, cron, profiles, skills, and settings. macOS, Windows, and Linux.
Git Worktrees
使用 git worktrees 和隔离检出在同一仓库中安全运行多个 Ailiv agent
Managed Scope
Administrator-pinned, user-immutable config and secrets via a system-level managed directory
Messaging Gateway
34 个项目
Profile 分发:共享完整 Agent
Profile 分发将一个完整的 Ailiv agent——个性、技能、cron 任务、MCP 连接、配置——打包为一个 git 仓库。任何有权访问该仓库的人都可以用一条命令安装整个 agent,就地更新,并保持自己的记忆、会话和 API 密钥不受影响。
Features
51 个项目
Local Models
Run models entirely on your own machine — no account, no API key, nothing leaves your computer.
Running Many Gateways at Once
Operate multiple profiles — each with its own bot tokens,
Which File Does What?
SOUL.md vs USER.md vs MEMORY.md vs AGENTS.md — a one-page map of the agent's files, who writes each one, and when the agent actually sees them
Connecting Desktop to Many Ailiv Instances
Register every Ailiv backend you own — the local runtime, remote gateways on
Docker
在 Docker 中运行 Ailiv Agent 以及将 Docker 用作终端后端
Sessions(会话)
会话持久化、恢复、搜索、管理及各平台会话跟踪
Checkpoints & Rollback
使用影子 git 仓库和自动快照为破坏性操作提供文件系统安全保障
安全
安全模型、危险命令审批、用户授权、容器隔离及生产部署最佳实践
Import from Other Agents
One-command import of a Claude Code (~/.claude) or OpenAI Codex CLI (~/.codex) setup into Ailiv — instructions, allowlists, MCP servers, skills, and memories.
Bot Mode
Turn your Ailiv profiles into a roster of named Bots — each with its own chat, role, model, memory, skills, and avatar. Bots run routines, share group chats, and message each other.
Secrets
3 个项目
skills
3 个项目
windows-native
P---