AI Skill Hub 强烈推荐:控制台 是一款优质的Agent工作流。AI 综合评分 8.0 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。
控制台 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。
控制台 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:npm 全局安装 npm install -g console # 方式二:npx 直接运行(无需安装) npx console --help # 方式三:项目依赖安装 npm install console # 方式四:从源码运行 git clone https://github.com/Cognipeer/console cd console npm install npm start
# 命令行使用
console --help
# 基本用法
console [options] <input>
# Node.js 代码中使用
const console = require('console');
const result = await console.run(options);
console.log(result);
# console 配置说明 # 查看配置选项 console --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 CONSOLE_CONFIG="/path/to/config.yml"
Open-source, self-hosted AI gateway for multi-tenant organizations — OpenAI-compatible LLM routing, RAG, agent orchestration, GPU fleet management, AI red-teaming, and cost optimization behind one production-ready console.
Community edition is available under AGPL-3.0. Commercial licensing, hosted deployments, and support agreements are available separately through Cognipeer.
Gateway - LLM Gateway — OpenAI-compatible chat completions, embeddings, batch, and moderations across OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, vLLM, Ollama, and more - Model Hub & Dynamic Routing — Fallback chains and per-model quota/rate limiting - Realtime — WebSocket voice agents with barge-in and tool-call events
Agents & Automation - MCP Hub — Curate, host, and discover Model Context Protocol servers (OpenAPI, remote, stdio) with per-tool controls - Agent Sandboxes — Isolated coding-agent dev environments with snapshot/fork/resume and port-forwarded previews - Browser Automation — Managed browser profiles, live sessions, and per-browser MCP endpoints - A2A Protocol — Publish Console-managed agents as Agent-to-Agent servers with agent cards - Prompt Management — Versioned templates with environment-based deployment (dev/staging/prod) and a built-in prompt optimizer
Knowledge & Retrieval - RAG / Knowledge Engine — Document ingestion, chunking, embedding, and retrieval - Web Crawler & Web Search — Scheduled or ad-hoc crawling plus a built-in search provider - Vector Store Management — Multi-provider vector operations (Pinecone, Chroma, Qdrant, and more) with built-in SQLite vector support - OCR & Rerankers — Layout/table-aware document extraction and Cohere-compatible reranking - Semantic Memory — Scoped memory stores with vector-based recall
Observability & Evaluation - Agent Tracing — Batch and streaming ingest, OTLP/HTTP JSON, and an OpenTelemetry exporter - Evaluations — Datasets, AI-assisted labeling, and accuracy scoring - Inference Monitoring & Alerts — Real-time monitoring for self-hosted inference servers with rule-based alerting
Safety & Compliance - Guardrails — PII detection, content moderation, prompt shields, and custom LLM-based evaluators - AI Red-Teaming — OWASP LLM Top 10 probes, campaigns, and attack runs - Audit Logging — Tenant-scoped audit trails
Infrastructure & Cost - GPU Fleet — Pooled GPU inference with MIG slicing, Hugging Face catalog deploys, and capacity planning - Cost Intelligence — Spend tracking, budgets, and automated optimization prescriptions - Multi-Tenant Architecture — Complete data isolation per tenant, projects, groups, and LDAP/SSO-ready auth - File Management — Multi-provider file storage with automatic Markdown conversion - Quota & Rate Limiting — Multi-dimensional quota enforcement with plan-level defaults
git clone https://github.com/Cognipeer/cognipeer-console.git
cd cognipeer-console
npm install
cp .env.example .env.local
npm run dev
The gateway starts with SQLite by default — no external database required.
Visit http://localhost:3000 to access the dashboard.
docker compose up -d
Or build and run manually:
docker build -t cognipeer-console .
docker run -p 3000:3000 -v ./data:/app/data -e JWT_SECRET=your-secret-here cognipeer-console
All configuration is managed through environment variables. See .env.example for the full list.
Key variables:
| Variable | Default | Description |
|---|---|---|
DB_PROVIDER | sqlite | Database backend (sqlite or mongodb) |
JWT_SECRET | — | **Required**. Secret for JWT signing |
MAIN_DB_NAME | cgate_main | Main database name |
CACHE_PROVIDER | memory | Cache backend (none, memory, redis) |
RATE_LIMIT_PROVIDER | mongodb | Rate limit backend (mongodb, memory, redis) |
BROWSER_BLOCK_PRIVATE_NETWORK | true | Block private-network egress from managed browser sessions |
CORS_ENABLED | false | Enable CORS for client APIs |
For the full configuration reference, see the Configuration Guide.
The gateway exposes an OpenAI-compatible API at /api/client/v1/:
```bash
If you are building an application against Cognipeer Console, prefer the official TypeScript/JavaScript SDK:
Use this repository and its docs for platform setup, deployment, providers, tenancy, auth, and raw HTTP API semantics.
Cognipeer Console 是一个开源的多租户 AI 网关,提供 LLM 服务、代理机器人协调、向量存储、RAG 管道、提示管理等功能。社区版可在 AGPL-3.0 许可下获得。商业许可、托管部署和支持协议可通过 Cognipeer 单独获取。
Cognipeer Console 的功能包括:多租户架构、LLM 网关、向量存储管理、RAG 管道等。
Cognipeer Console 的环境依赖包括 Node.js 20+ 和 npm。
安装 Cognipeer Console 可以使用以下步骤:克隆仓库、安装依赖、配置环境变量、启动开发环境。也可以使用 Docker 部署。
Cognipeer Console 的使用教程包括启动开发环境、访问控制台等。
Cognipeer Console 的配置管理通过环境变量进行,包括数据库提供者、JWT 密钥等关键参数。
Cognipeer Console 暴露了一个 OpenAI 兼容的 API,位于 /api/client/v1/ 路径下。
高质量的AI工作流项目
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。
总体来看,控制台 是一款质量优秀的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 | console |
| 原始描述 | 开源AI工作流:Operate inference, LLM Gateways, vector stores, tracing, guardrails, RAG, config。⭐24 · TypeScript |
| Topics | AI工作流TypeScript |
| GitHub | https://github.com/Cognipeer/console |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间:2026-06-01 · 更新时间:2026-06-01 · 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