#8080th of 102 in Agent platforms
onecli
Runs a sandboxed agent per employee behind a credential-injecting gateway
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.6k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
1,939 on 25 Apr 20263,645 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OneCLI creates one sandboxed agent per team member, reachable from a Next.js dashboard or Slack. Outbound traffic passes through a Rust gateway that injects credentials, so agents never see secrets, and enforces a shared policy with human approval for sensitive actions. Secrets are stored AES-256-GCM encrypted, or fetched on demand from Bitwarden or 1Password.
Who it is for: Teams self-hosting a controlled, sandboxed agent for each employee
Strengths
- Gateway injects credentials via MITM proxy, so agents never hold secrets
- Per-agent sandbox, memory, skills and schedule, managed from one dashboard
- Runner is outbound-only: works behind NAT with no ingress or tunnel
- Helm chart for Kubernetes plus a pnpm-based self-host path
Weaknesses
- Enterprise features in ee/ directories need a paid subscription for production use
- Multi-component stack: dashboard, API server, gateway, runner, supervisor, Postgres
- Self-host setup uses pnpm and mise; no Docker or Compose file detected
- Slack is the only chat channel mentioned besides the dashboard
What it needs
- Docker + Compose
- Needs PostgreSQL, pnpm, Slack (optional), Bitwarden or 1Password (optional), Kubernetes (optional)
- port 10254
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent platforms
See all 102| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, served as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |