agenticos
Active·★ 114·Apache-2.0·Updated 2026-10-22
AgenticOS is an open-source (Apache-2.0), self-hosted layer for building, sharing and governing AI agents across a company. Teams configure agents in the browser with instructions, a model and tools, connect them to documents and apps, and publish them to web chat, Slack, Mattermost, Telegram, a website widget or an API. Administrators control access, spending limits and approvals, and every run is recorded. It runs with Docker Compose and works with 27 model providers.
#agent-control-plane#agent-framework#agentic-ai#agentic-os#agents#ai-agents#ai-governance#fastapi
01
Features
01Build and publish agents in the browser without code changes or releases
02Publish to web chat, Slack, Mattermost, Telegram, a website widget or an API
03Access control by roles and groups, budgets, approvals and recorded runs
04Document knowledge with citations, reusable skills and published result pages
05Self-hosted with Docker Compose; 27 model providers including Ollama and vLLM
02
Compatibility
Docker
Docker Compose
Verified via docs
Slack
Channel
Verified via docs
Ollama
Local models
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/vstorm-co/agenticos/main/scripts/quickstart.sh | bash
04
Use cases
↳Give a company one governed place to build and share internal agents
↳Automate repeated work over documents and tools such as reports, support answers and contract checks
↳Keep agent usage, spend and results visible to IT and security teams
05
Alternatives
agentos★ 682
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.
KiroCrew★ 4.5k
A persistent workspace for development work that self-improves and continues beyond one session.
agent-device★ 5.1k
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
Intercept★ 32
The enforcement layer for AI agents. Intercept enforces hard, deterministic limits on what agents can do at the MCP transport layer — before execution.
agentdescent★ 207
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
Comments
Log in to leave a comment
No comments yet. Be the first!