简侎 AI分端器方式
AI Skill Hub 推荐使用：简侎 AI分端器方式 是一款优质的Agent工作流。AI 综合评分 7.5 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。
📚 深度解析
简侎 AI分端器方式 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 7.5 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
简侎的安全源常用的手本器方式，可代为当前的手机器方式。
简侎 AI分端器方式 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
📖 中文文档
简侎的安全源常用的手本器方式，可代为当前的手机器方式。
简侎 AI分端器方式 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 克隆仓库 git clone https://github.com/mjason/long cd long # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 查看帮助 long --help # 基本运行 long [options] <input> # 详细使用说明请查阅文档 # https://github.com/mjason/long
# long 配置说明 # 查看配置选项 long --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export LONG_CONFIG="/path/to/config.yml"
Long
English · 简体中文
A single-process, multi-user LLM agent runtime on Elixir/OTP — for a household or a small team. Phoenix for the UI, Ash for the data layer, Oban for scheduled tasks, ReqLLM for provider abstraction.
Long started as a port of the Python GenericAgent to Elixir, borrowing its core shape — one session → ReAct loop → tools + memory + skills. The design has since diverged substantially: on the BEAM it gets real concurrency, fault tolerance, and long-lived push messaging natively (one supervised GenServer per session rather than a bolted-on Python process model), and the agent's capability layer has been rebuilt on mature, standard technology rather than a bespoke tool protocol — most notably GraphQL as the agent's primary skill (see below).
It's web-first: you don't run a CLI to talk to it. Open the browser, and chat, configuration, memory, channels, and scheduled tasks are all just pages.
Features
- GraphQL capability layer — one introspectable
graphqltool gives the agent read/write over its whole data world (see above). - Groups & members (multi-tenant) — a deployment hosts one or more groups (a family, a small team). Each member links their own WeChat / Telegram by sending
/bind <code>, gets an isolated per-member code workspace + personal skills, and can message other members in the group ("notify …"). One owner, many members. - Sandboxed code execution —
code_runruns TypeScript/JavaScript on a managed Deno binary, sandboxed (read/write) to the caller's per-member workspace;bashis there for shell. No Python — Deno auto-downloads on first use. - Per-chat language (i18n) — every bot string resolves through a fallback chain (channel → member → group → platform-detected → system default) and is overridable at
/manage/phrases; set a system-wide default language in one click. - Web-first LiveView UI —
/chat(streaming output + tool-call display + live memory side-rail + AI-generated session titles) and/managefor everything else. - Four-tier memory:
- L1
WorkingCheckpoint(onekey_inforow per session) - L2
GlobalMemory/SessionMemory(fact / preference / goal / decision, with importance + recency decay) - L3 Anthropic-compatible Skills (
SKILL.md+ scripts/references/assets), scoped per-member or shared group-wide (promote a personal skill to global, or view a skill's fullSKILL.md, at/manage/skills); the filesystem is the source of truth, a watcher drives an ETS index - L4
SessionArchive(session archival + LLM summary) - Multi-provider LLM routing — ReqLLM speaks 20+ providers natively (openai / anthropic / google / groq / deepseek / openrouter / mistral / ollama / xai / bedrock / …); wire protocol is configurable, one alias is the default.
- Unified admin at
/manage— LLM configs, memory editing, skill browsing, groups & members, channels, phrases (i18n), session management, search providers, scheduled tasks, secrets — all LiveView, no ash_admin dependency. - Scheduled tasks — Oban-driven; the LLM schedules its own via GraphQL
createScheduledTask, or you create them by hand at/manage/scheduled. - Multi-account channels — host several WeChat accounts and/or Telegram bots at once, each bound to a different member; inbound auto-tags the sender, outbound routes back through the exact account the chat arrived on. Onboarded at
/manage/credentials. - Web search aggregation — Tavily / Brave API + SERP scrapers, RRF multi-source merge, providers configured at
/manage/search. - Real headless browsing — the Obscura CLI (a Rust Chromium fork) powers the
web_scan/web_execute_jstools. - Error observability — ErrorTracker dashboard, a
:loggercrash backstop, transparent exponential-backoff retry on LLM calls. - In-conversation control —
/clearwipes a session,/statusasks what the agent is doing,/btw <note>interjects mid-run,/bind <code>links this chat to a member.
One-line install (macOS / Linux)
Prebuilt releases cover macos-arm64, linux-x64, and linux-arm64:
curl -fsSL https://raw.githubusercontent.com/mjason/long/main/install.sh | bashThe script:
- pulls the latest tarball from GitHub Releases and extracts it to
~/.long/, - on first run generates
~/.long/env(with an auto-generatedSECRET_KEY_BASE,DATABASE_PATH, …), - writes the
~/.long/runlauncher and the~/.long/serviceautostart controller.
$EDITOR ~/.long/env # usually nothing to change
~/.long/run # start; open http://localhost:4000Make it start on boot (no root, no unit-file editing):
~/.long/service install # enable autostart (launchd / systemd-user)
~/.long/service status # is it registered + running?
~/.long/service logs # tail run.log
~/.long/service uninstall # disable autostartInstaller environment variables:
| Variable | Default | Meaning |
|---|---|---|
LONG_INSTALL_DIR | ~/.long | install target |
LONG_VERSION | latest | pin a version, e.g. v0.2.9 |
Docker
A self-contained image bakes in the mix release plus Deno and Obscura — nothing is downloaded on first run. The repo ships a ready docker-compose.yml:
services:
long:
image: ghcr.io/mjason/long:latest # or build locally: build: .
ports: ["4000:4000"]
environment:
SECRET_KEY_BASE: ${SECRET_KEY_BASE} # generate once: openssl rand -base64 48
PHX_HOST: ${PHX_HOST:-localhost}
# LONG_CHECK_ORIGIN: "true" # set when exposing to the internet
volumes: ["long_data:/data"] # SQLite DB + skills + workspace + memory
restart: unless-stopped
volumes:
long_data:From a clone of the repo:
```bash export SECRET_KEY_BASE=$(openssl rand -base64 48) docker compose up -d # build + run
Install your first Skill (optional)
```bash mkdir -p priv/agent/skills/hello-world/scripts
Quick start
cat > priv/agent/skills/hello-world/SKILL.md <<'MD'
name: hello-world description: Demo skill — takes a name arg, returns a greeting string.
hello-world
Run scripts/hello.py "<name>". MD
cat > priv/agent/skills/hello-world/scripts/hello.py <<'PY' import json, sys name = (json.loads(sys.argv[1]) if len(sys.argv) > 1 else {}).get("name", "world") print(json.dumps({"greeting": f"hello, {name}"}, ensure_ascii=False)) PY
mix long.skill reindex # or restart the server; the watcher also picks it up ```
Next conversation, the LLM sees hello-world under # Available skills and can skill_read then code_run it. The format is fully compatible with Anthropic Agent Skills, so you can git clone https://github.com/anthropics/skills priv/agent/skills/ to grab the official repo wholesale.
tags: [demo]
Configure your first LLM
Open /manage/llms → New LLM:
| Field | Example |
|---|---|
| Alias | claude_main |
| Provider | anthropic |
| Wire protocol | anthropic_messages |
| Model | claude-sonnet-4 |
| API base | https://api.anthropic.com (or a proxy) |
| API key | sk-ant-…, or leave blank to use api_key_env_var |
| Set as default | ✓ |
Save, go back to /chat, and new sessions bind to this alias automatically. The same flow works for OpenAI / Google / Groq / DeepSeek / any ReqLLM-supported provider.
Configuration
Configure from the web, not from files. Almost everything — LLMs, search providers, channels, scheduled tasks, memory, secrets — lives in the DB and is edited at /manage. There's no config file to redeploy for day-to-day changes.
The only file-level config is a handful of filesystem roots, under :long, Long.Agent in config/config.exs (the installed release reads these from ~/.long/env instead):
config :long, Long.Agent,
memory_root: "priv/agent/memory", # legacy GenericAgent-compatible path
skill_root: "priv/agent/skills", # L3 skill dir (SKILL.md lives here)
workspace_root: "priv/agent/workspace" # root for code_run / file_* toolsEverything else is a page in /manage (or, if you prefer, an IEx call like Long.Agent.register_llm/1).
CLI tools
| Command | Purpose |
|---|---|
mix phx.server | start the web server (default port 4000) |
mix long.skill list / reindex / remove NAME | skill index management |
mix long.wechat.login | WeChat QR login + buf persistence |
iex -S mix | REPL: Long.Agent.list_sessions(), etc. |
mix test | test suite |
mix precommit | compile --warnings-as-errors + format + test |
简侎的手本器方式当前可代为手机器方式。可代为当前的手机器方式。
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
🔗 相关工具推荐
❓ 常见问题 FAQ
总体来看，简侎 AI分端器方式 是一款质量良好的Agent工作流，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | long |
| 原始描述 | 开源AI工作流：Single-binary LLM agent runtime built on Elixir/OTP: chat UI, 4-tier memory, Ant。⭐24 · Elixir |
| Topics | workflowai-agentanthropic-skillsash-frameworkchatelixir |
| GitHub | https://github.com/mjason/long |
| License | MIT |
| 语言 | Elixir |
收录时间：2026-06-09 · 更新时间：2026-06-09 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。