Personal sandboxed agents
Provision an AI agent for each employee, with each agent running in its own isolated environment.
OneCLI
Freemium
OneCLI is an open-source platform for giving employees personal AI agents that can work across company tools. It provides isolated sandboxes, gateway-enforced policies, scoped credentials, approvals, and audit logs for team use.
什么是 OneCLI？
OneCLI is an open-source platform for running AI agents as a team. It provisions a personal agent for each employee and lets people interact with that agent from the web, Slack, or the terminal. Agents can work across connected business tools while OneCLI controls how requests reach those services.
The platform separates agents from the credentials they use. Credentials remain in an encrypted vault and are attached by the gateway for individual requests, so keys are not exposed to the agent, model, prompts, environment variables, or logs. Each agent runs in an isolated sandbox, while policies can govern network requests and sensitive actions.
OneCLI is intended for business workflows where employees need AI assistance with operational data or tools but organizations need review and traceability. Examples shown on the product site include Salesforce updates, approved metric queries in Snowflake, and investigations that start from Datadog alerts and open code patches as pull requests.
OneCLI 能做什么？
Gateway-based credential handling
Store credentials in an encrypted vault and attach scoped, expiring access at the gateway for each request; agents and models do not see the underlying keys.
Network-level policy controls
Block endpoints, rate-limit agents, scope access by employee, and require human approval for sensitive operations. Controls apply to MCP calls, CLI commands, shell requests, and HTTP traffic from agent-written code.
Approval and audit workflows
Configure which changes require approval, pause an agent before execution, and retain an audit trail of requests and actions by employee.
Multi-channel access
Let employees use the same agent identity, permissions, and audit trail from the web, Slack, or the terminal.
Tool and framework connectivity
Connect services such as Salesforce, HubSpot, Zoho CRM, Snowflake, Supabase, MongoDB, Slack, Gmail, Outlook, Notion, Linear, Google Drive, Datadog, Sentry, and GitHub. OneCLI also supports agent frameworks and pipelines that make HTTP calls, including OpenClaw, NanoClaw, IronClaw, Dify, n8n, and OpenHands.
使用场景
“Controlled CRM operations”
A RevOps agent can read meeting information, match records, prepare bulk Salesforce updates, and pause for approval before writes are applied.
“Self-service business intelligence”
A BI agent can answer plain-language questions in Slack by selecting approved metric definitions, running a query in Snowflake, and returning the result.
“Incident investigation and remediation”
An SRE or developer agent can begin with a Datadog alert, trace an error to a commit, write a patch, and open a pull request for review.
“Recurring operations”
Teams can schedule repeated tasks, such as reassigning Salesforce accounts from a handoff list in Notion, while approval rules determine whether the agent may make the final changes.
“Team-wide agent access”
Organizations can give employees individual agents without distributing shared API keys, and can disable an agent during offboarding while preserving its audit history.
常见问题
How do employees use their agents?
Employees can chat with their agent in the web app, Slack, or the terminal. The agent keeps the same identity, permissions, and audit trail across those entry points.
Can agents access API keys directly?
No. Credentials are stored in an encrypted vault and attached at the gateway boundary for individual requests. They are not exposed in environment variables, prompts, or logs.
What kinds of actions can administrators control?
Administrators can block endpoints, set per-agent rate limits, scope credentials, and require human approval for sensitive operations. These rules are enforced outside the agent and model at the network layer.
Does OneCLI require a specific agent framework?
No. The FAQ describes it as framework-agnostic and lists OpenClaw, NanoClaw, IronClaw, Dify, n8n, OpenHands, and custom HTTP-based pipelines as compatible options.
Can OneCLI be self-hosted?
The source describes the core code as Apache-2.0 licensed and says it can be self-hosted with a one-line install. The pricing page lists self-hosted deployment as an Enterprise feature; OneCLI Cloud is available as the managed alternative.
快速信息
- Category
- Team AI agent platform
- Deployment
- OneCLI Cloud or self-hosted; Enterprise self-hosting is listed on the pricing page
- Access channels
- Web, Slack, and terminal
- Security model
- Isolated per-employee sandboxes, gateway-mediated credentials, policy enforcement, and audit logging
- Free plan
- $0, with $5 in AI model credits and 500 integration calls per month; no credit card required
- Open-source license
- Core code is Apache-2.0 licensed
OneCLI 流量分析
流量数据仅供参考。
- 域名评分
- 35
OneCLI 替代品
Edgee
www.edgee.ai
Edgee is an agent gateway for coding teams that reduces token usage, routes requests across models, and provides usage visibility. Its Compression V2 works as a drop-in CLI layer for Claude Code, Codex, OpenCode, Cursor, and other supported agents.
Docker MCP Enterprise Gateway
www.docker.com
Docker MCP Enterprise Gateway governs how MCP-compatible clients access approved servers and tools. It applies identity-aware policy, supplies credentials from an approved secret store, and records tool-call decisions for enterprise teams.
Agent Router
theagentrouter.ai
Agent Router is an open-source Go project for managing unified access to generative AI services through Envoy Gateway. It is intended for teams that want a gateway-based control point for AI service traffic and related agent or MCP workloads.
treg.to
treg.to
treg.to is an API gateway and MCP server for calling tools and data providers through one endpoint and credential. It helps agents and developers use cataloged SEO, enrichment, advertising, social, scraping, and other data tools without managing separate provider keys for every metered call.
Cohesor
www.cohesor.com
Cohesor is an AI gateway and control plane for routing model requests, compressing agent context, governing spend, and brokering MCP tool calls. It is designed for teams running internal or customer-facing AI agents.
Obot
obot.ai
Obot is an open-source enterprise AI control plane and MCP gateway for deploying, governing, and auditing AI agents, MCP servers, and Skills. It helps organizations centralize access policies, discovery, authentication, and activity records across AI tooling.