Categories
Developer Tools AI Agents Self-Hosted AI Project Management Agent Orchestration Multi-Agent Systems LLM Operations AI WorkforceStars
Forks
Watchers
Developer links
Hezo
A whole company of AI agents, from a CEO to engineers, designers, and analysts, works inside Hezo under budgets, approvals, and sandboxes you control. Starting a project means picking a ready-made marketplace team (App Team, Social Media Marketing, or Investment Portfolio), using a template, or asking the CEO to assemble one, and the org chart can be reshaped while work continues. Agents pull tasks from a board with nested sub-tasks, wake on heartbeats, pause at approval gates, and push verified commits to your GitHub repositories. Each agent can run on its own model, whether Claude, GPT, Gemini, Grok, Kimi, DeepSeek, GLM, OpenRouter, Ollama, or LM Studio, using API keys or an Anthropic or OpenAI subscription signed in from the UI. Token budgets pause runs at their limits, cost per run stays visible, and a container-hours ledger enforces a monthly allowance. Every project works in its own container, and stored secrets reach agents only as placeholders that an egress proxy swaps for real values on hosts you allowed. A Coach agent turns lessons from finished tasks into durable rules, while documents, skills, and full-text search hold shared knowledge. Message the CEO from Telegram, Slack, or Discord, or drive Hezo from any MCP client through its built-in MCP server. The web app speaks 12 languages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0-or-later licensed.
Benefits
- Run Agents Like a Company
- Org charts with a CEO, Captains, and specialist workers turn a pile of terminal sessions into one managed team, and you can restructure roles while a project keeps running.
- Spending Stays Under Hard Caps
- Per-agent and per-project token budgets pause runs at their limits and resume when the window rolls over, while a container-hours ledger stops new sandboxes once the monthly allowance is spent.
- Secrets Stay Behind an Egress Proxy
- Stored secrets reach agents only as placeholders; an egress proxy swaps in the real value for hosts you allowed and blocks the request anywhere else. The model-provider key is the one exception.
- Any Model, Per Agent
- Give each agent its own provider: Claude, GPT, Gemini, Grok, Kimi, DeepSeek, GLM, OpenRouter, or local Ollama and LM Studio, with API keys or an Anthropic or OpenAI subscription.
Features
- Org Charts and Teams
- A global CEO and Coach sit above per-team Captains and workers, with marketplace teams, templates, hiring, and snapshots to reuse a tuned structure on the next project.
- Task Board and Approvals
- Nested sub-tasks, heartbeat wake-ups, and approval gates keep long runs moving while consequential actions, such as a proposed hire, wait for your explicit sign-off.
- Sandboxed Project Containers
- Every project runs in its own container with memory caps and verified git commits, on local Docker or a managed sandbox service you can switch between at any time.
- Coach and Shared Knowledge
- A Coach writes lessons from finished tasks back onto agents as durable rules, while documents, skills, version history, and full-text search keep project knowledge in one place.
- Chat and MCP Integrations
- Talk to the CEO from Telegram, Slack, or Discord, drive it from any MCP client through its built-in MCP server, and connect agents to MCP servers or REST APIs.
- Model Meta-Harness
- A meta-harness runs each model in its own first-party CLI, such as Claude Code or Codex, and gives every model the same tools, skills, memory, and sandbox.