Facio智能工作流引擎 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.8 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
Facio智能工作流引擎 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。
Facio智能工作流引擎 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。
# 方式一：pip 安装（推荐）
pip install facio
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install facio
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/placet-io/facio
cd facio
pip install -e .
# 验证安装
python -c "import facio; print('安装成功')"
# 命令行使用
facio --help
# 基本用法
facio input_file -o output_file
# Python 代码中调用
import facio
# 示例
result = facio.process("input")
print(result)
# facio 配置文件示例（config.yml） app: name: "facio" debug: false log_level: "INFO" # 运行时指定配置文件 facio --config config.yml # 或通过环境变量配置 export FACIO_API_KEY="your-key" export FACIO_OUTPUT_DIR="./output"
<p align="center"> <img src="logo/facio-readme-hero.svg" alt="facio" width="100%" /> </p>
<p align="center"> <strong>A long-running, human-in-the-loop runtime for reliable AI work.</strong><br/> Built to collaborate with the operator, not to erase the operator. </p>
<p align="center"> <em>self-improving · auditable · resumable · approval-gated · multimodal</em> </p>
<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
curl -fsSL https://raw.githubusercontent.com/placet-io/facio/main/quickstart/setup.sh | FACIO_DEBUG=1 bash -s -- --yes
**After install** — manage from `./facio/`:
The first agent is named Facio Agent. When you scale, agents use stable internal hostnames (facio-1, facio-2, ...) and human-readable Placet names like Facio Agent (#1), Facio Agent (#2), ... instead of Docker-generated container IDs. Each agent gets its own data dir under ./volumes/facio/<hostname>/ and auto-registers with Placet over the docker network.
Custom overrides (Traefik, external networks, port bindings, hardening, …): setup drops a docker-compose.override.yml.template next to the compose files as a menu of opt-in snippets (Traefik, external mode port binding, dropping SYS_ADMIN on rootless hosts, …). Copy it to docker-compose.override.yml, keep only the sections you need, and run ./facio up. Docker auto-loads docker-compose.override.yml on top of the main docker-compose.yml, so the main file stays untouched. In external mode setup bootstraps a minimal docker-compose.override.yml for you (just the host port binding) when none exists yet — feel free to edit it.
<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
git clone https://github.com/placet-io/facio.git
cd facio
uv sync --all-extras
facio onboard
facio agent<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
Prerequisites: Docker 24+ with Compose v2.
curl -fsSL https://raw.githubusercontent.com/placet-io/facio/main/quickstart/setup.sh | bashThat's it. The script detects your OS, verifies Docker, fetches the public compose file into ./facio/, asks for the initial Placet admin email and password, generates any missing secrets, pulls ghcr.io/placet-io/{placet,facio}:latest, and runs docker compose up -d for you.
Facio starts with one agent by default. If you leave the password blank, setup generates one and prints it at the end together with the Placet URL where the Facio agent is available. Default URL: http://localhost:8080.
Variants:
```bash
|
01 / Approval-heavy operations Internal tooling, release prep, customer support escalations, incident follow-up, or account workflows where the agent should move fast but still stop before crossing unclear boundaries. |
02 / Personal operator runtime One persistent agent that keeps context across sessions, learns preferences, remembers bugs and facts separately, and can keep working for weeks instead of starting from zero every day. |
|
03 / Self-debugging assistants Workflows where the runtime should be able to inspect audit trails, read its own logs, understand recent failures, and recover without the operator manually stitching context back together. |
04 / Secure AI collaboration Setups that need secret redaction, isolated credential handling, tool policy gates, guardrails, and explicit operator control instead of a model receiving broad silent access. |
|
05 / Tool-rich knowledge work Research, coding, ops, documentation, and mixed human/agent execution where runtime model switching, MCP tooling, reusable skills, and scripts should stay manageable while the agent is live. |
06 / File-heavy HITL workflows Reviews, approvals, attachments, structured forms, and iteration chains where plain chat is too weak and the operator needs a real frontend for supervision. |
<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
curl -fsSL https://raw.githubusercontent.com/placet-io/facio/main/quickstart/setup.sh | bash -s -- --external
When the management API is enabled, Facio exposes the central versioning and self-improvement surfaces under the same bearer-authenticated /api/v1/* API as the rest of management:
| Endpoint | Purpose |
|---|---|
GET /api/v1/agent/versions | List central agent versions. |
POST /api/v1/agent/versions/checkpoint | Create a manual checkpoint when tracked agent state changed. |
GET /api/v1/agent/versions/{sha} | Inspect one central agent version. |
GET /api/v1/agent/versions/{sha}/diff | Return a redacted diff for a version. |
POST /api/v1/agent/versions/{sha}/rollback | Restore tracked agent-owned files to a version and rehydrate MCP, policy, and cron runtime state where possible. |
GET /api/v1/improvement/runs | List self-improvement runs. |
POST /api/v1/improvement/runs/{runId}/approve | Approve and optionally apply a run. |
POST /api/v1/improvement/runs/{runId}/reject | Reject a run. |
POST /api/v1/improvement/runs/{runId}/rollback | Roll back an applied run. |
Self-improvement settings live under agents.defaults.self_improvement and can also be managed through the settings API. The main controls are enabled, mode, auto_triggers, interval_h, scopes, max_iterations, optional model_override / provider_override, and validation_level.
GitHub backup sync is opt-in under agents.defaults.github_backup. If it is unset or disabled, Facio does not call GitHub and keeps using only the local GitStore. To enable remote sync, set FACIO_GITHUB_BACKUP_ENABLED=true plus optional FACIO_GITHUB_BACKUP_OWNER=<owner> and FACIO_GITHUB_BACKUP_REPO=facio-backup, or FACIO_GITHUB_BACKUP_REMOTE_URL=https://github.com/<owner>/<repo>.git. On startup, Facio checks the GitHub repo and creates it as private when it is missing (FACIO_GITHUB_BACKUP_CREATE_REMOTE=true, FACIO_GITHUB_BACKUP_PRIVATE=true by default). Push/pull authentication uses GH_TOKEN, GITHUB_TOKEN, or FACIO_GITHUB_TOKEN from the environment, and can also use a Placet secret named GITHUB_TOKEN by default. Secrets stay in the CredentialStore outside the workspace git repository.
<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
Detailed documentation is being reorganized. This README stays product-first on purpose.
|
LLM providers OpenAI · Anthropic · OpenRouter · Azure OpenAI · GitHub Copilot · OpenAI Codex · OpenCode Zen Go · any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, …) via the compat provider. |
Channels Placet (primary) · Telegram · Discord · Slack · Email · Microsoft Teams · CLI REPL · OpenAI-compatible HTTP · A2A 1.0. |
Tools & protocols MCP servers (stdio & SSE, runtime add/remove) · workspace skills · custom Python scripts · web fetch & search · exec sandboxed via bwrap · image and video generation · transcription. |
|
Auth & secrets OAuth flows for channels and skills · HITL credential capture · per-skill credential scopes · ${credentials.KEY} placeholders · operator-controlled exec env-var whitelist.
|
Persistence Git-tracked workspace · SQLite audit log (WAL) · token-usage rollups · file-based session history · resumable cron jobs · on-disk runtime logs with rotation. |
Management Bearer-auth /api/v1/* for sessions, cron, channels, skills, MCP, audit, usage, policy, settings, agent versions, and improvement runs · agent card override at workspace/agent-card.json · slash commands for runtime control.
|
<p align="center"><img src="logo/facio-readme-separator.svg" alt="" width="100%" /></p>
设计理念先进，强调安全可追踪的AI工作流。代码活跃度一般，适合对流程可控性要求高的场景应用。
该工具使用 AGPL-3.0 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
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。
⚠️ AGPL 3.0 — 最严格的 Copyleft，网络服务端使用也需开源，SaaS 使用受限。
经综合评估，Facio智能工作流引擎 在Agent工作流赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | facio |
| 原始描述 | 开源MCP工具：A proactive AI agent for secure, traceable, human-in-the-loop task execution ove。⭐104 · Python |
| Topics | MCP工具AI代理工作流自动化人机交互任务执行 |
| GitHub | https://github.com/placet-io/facio |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间：2026-05-21 · 更新时间：2026-05-22 · License：AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端