# 100monkeys.ai

> 100monkeys.ai builds AEGIS, a self-hosted orchestrator that runs autonomous agents in isolated, policy-enforced runtimes with durable FSM state, and four products alongside it: Carbon Forge, Your Zaru, Zaru CLI and Grill My Idea. AEGIS is open source under AGPL-3.0 and installs with one command: `curl -fsSL https://get.100monkeys.ai | bash`

AEGIS bounds what an agent can do at the infrastructure layer rather than in the prompt. Generate, execute, evaluate, refine: the loop runs until deterministic validators pass. The membrane around it enforces isolation and policy on every tool call, and each run is a durable state machine.

## AEGIS

- [100monkeys.ai](https://100monkeys.ai/): the company site, with the AEGIS overview and the install command
- [AEGIS documentation](https://docs.100monkeys.ai): the platform docs
- [Getting started](https://docs.100monkeys.ai/docs/getting-started): install and run a first agent
- [AEGIS documentation for LLMs](https://docs.100monkeys.ai/llms.txt): the docs index in llms.txt form
- [aegis-orchestrator on GitHub](https://github.com/100monkeys-ai/aegis-orchestrator): the source, AGPL-3.0

## Products

- [Carbon Forge](https://carbonforge.dev/): code, files and prose in one record on the server, which people and agents read and write through the same tools over MCP. Public workspaces are free, and every account includes one free private workspace
- [Your Zaru](https://myzaru.com/): a personal AI companion that works alongside you, remembers you and shows its work
- [Zaru CLI](https://github.com/100monkeys-ai/zaru-cli): a terminal coding agent that keeps its execution loop in view, open source under Apache-2.0
- [Grill My Idea](https://grillmyidea.com/): market research for a startup idea, before you build it

## Read

- [FAQ](https://100monkeys.ai/faq): short answers on self-hosting an agent orchestrator, keeping credentials away from agents, durable agent workflows and accountability
- [FAQ in Spanish, Portuguese, Japanese, German, French, Korean, Chinese, Italian and Hindi](https://100monkeys.ai/faq/es/): the same answers translated, one page per language at /faq/es/, /faq/pt/, /faq/ja/, /faq/de/, /faq/fr/, /faq/ko/, /faq/zh/, /faq/it/, /faq/hi/
- [Red levers: traceable, deterministic agents in production](https://100monkeys.ai/papers/red-levers): a paper by Jeshua ben Joseph, 100monkeys AI, Inc., CC BY 4.0 ([PDF](https://100monkeys.ai/papers/red-levers.pdf))
- [Datasheets](https://100monkeys.ai/datasheets/): one-page PDFs for AEGIS, Carbon Forge and Zaru
- [Blog](https://100monkeys.ai/blog/): essays from 100monkeys.ai ([RSS](https://100monkeys.ai/blog/rss.xml))
- [Guides in Spanish, Portuguese, Japanese, German, French, Korean, Chinese, Italian and Hindi](https://100monkeys.ai/blog/es/): one index per language at /blog/es/, /blog/pt/, /blog/ja/, /blog/de/, /blog/fr/, /blog/ko/, /blog/zh/, /blog/it/ and /blog/hi/
- [Full text for LLMs](https://100monkeys.ai/llms-full.txt): the English FAQ, paper, datasheets page and guides in one Markdown file
- [Blame that remembers why](https://100monkeys.ai/blog/blame-that-remembers-why): what a change should carry when the author was an agent
- [The approval is the product](https://100monkeys.ai/blog/the-approval-is-the-product): why an agent orchestrator should make you say yes
- [Run a scheduled agent with AEGIS](https://100monkeys.ai/blog/run-a-scheduled-agent-with-aegis): Put an AEGIS agent on a timer, fire it once by hand, and read each run: started, skipped, refused or paused. Every field from the public docs.
- [Ejecuta un agente programado con AEGIS](https://100monkeys.ai/blog/es/run-a-scheduled-agent-with-aegis) (es): Pon un agente de AEGIS en un temporizador, dispáralo una vez a mano y lee cada ejecución: iniciada, omitida, rechazada o pausada. Según la documentación.
- [Rode um agente agendado com o AEGIS](https://100monkeys.ai/blog/pt/run-a-scheduled-agent-with-aegis) (pt): Coloque um agente do AEGIS num timer, dispare-o uma vez à mão e leia cada execução: iniciada, pulada, recusada ou pausada. Tudo vem da documentação.
- [AEGIS でエージェントをスケジュール実行する](https://100monkeys.ai/blog/ja/run-a-scheduled-agent-with-aegis) (ja): AEGIS のエージェントをタイマーに載せ、手動で一度起動し、各実行の結果(開始・スキップ・拒否・一時停止)を読みます。項目はすべて公開ドキュメントから。
- [Reading an AEGIS execution log and a sealed tool call](https://100monkeys.ai/blog/reading-an-aegis-execution-log): Read an AEGIS run from its execution record to its iteration log to the SEAL envelope and audit event behind each tool call, allowed or refused.
- [Cómo leer el log de AEGIS y una llamada sellada](https://100monkeys.ai/blog/es/reading-an-aegis-execution-log) (es): Lee una ejecución de AEGIS desde su registro hasta su log de iteraciones, el sobre SEAL y el evento de auditoría de cada llamada, permitida o rechazada.
- [Como ler o log do AEGIS e uma chamada selada](https://100monkeys.ai/blog/pt/reading-an-aegis-execution-log) (pt): Leia uma execução do AEGIS do registro ao log de iterações, até o envelope SEAL e o evento de auditoria de cada chamada, permitida ou recusada.
- [AEGIS の実行ログと封印されたツール呼び出しを読む](https://100monkeys.ai/blog/ja/reading-an-aegis-execution-log) (ja): AEGIS の実行を、実行レコードから反復ログ、各ツール呼び出しの SEAL エンベロープと監査イベントまで読みます。許可された呼び出しも拒否された呼び出しも。
- [AEGIS on Firecracker: what the docs describe today](https://100monkeys.ai/blog/aegis-on-firecracker): Firecracker support in AEGIS is planned, not shipped. Check a host for KVM, read the documented config, and run the Podman path that works now.
- [AEGIS en Firecracker: lo que describe hoy la documentación](https://100monkeys.ai/blog/es/aegis-on-firecracker) (es): El soporte de Firecracker en AEGIS está planificado, no publicado. Comprueba KVM en un host, lee la configuración documentada y usa hoy la vía Podman.
- [AEGIS no Firecracker: o que a documentação descreve hoje](https://100monkeys.ai/blog/pt/aegis-on-firecracker) (pt): O suporte a Firecracker no AEGIS está planejado, não lançado. Verifique KVM num host, leia a configuração documentada e use hoje o caminho Podman.
- [Firecracker 上の AEGIS: ドキュメントが今述べていること](https://100monkeys.ai/blog/ja/aegis-on-firecracker) (ja): AEGIS の Firecracker 対応は計画段階で、まだ提供されていません。ホストの KVM を確認し、記載された設定を読み、今動く Podman の手順を使います。
- [Install AEGIS on Ubuntu and run an approved task](https://100monkeys.ai/blog/install-aegis-on-ubuntu-vps): Install AEGIS on a fresh Ubuntu server with one command, run an agent, then gate its result behind a human approval. Every step from the public docs.
- [Instala AEGIS en Ubuntu y ejecuta una tarea aprobada](https://100monkeys.ai/blog/es/install-aegis-on-ubuntu-vps) (es): Instala AEGIS en un servidor Ubuntu con un solo comando, ejecuta un agente y deja su resultado tras una aprobación humana. Todo, de la documentación.
- [Instale o AEGIS no Ubuntu e rode uma tarefa aprovada](https://100monkeys.ai/blog/pt/install-aegis-on-ubuntu-vps) (pt): Instale o AEGIS num servidor Ubuntu com um comando, rode um agente e deixe o resultado atrás de uma aprovação humana. Cada passo vem da documentação.
- [Ubuntu に AEGIS を入れて承認付きタスクを実行する](https://100monkeys.ai/blog/ja/install-aegis-on-ubuntu-vps) (ja): 新しい Ubuntu サーバーに AEGIS をコマンド1つでインストールし、エージェントを動かして、その結果を人間の承認の後ろに置きます。手順はすべて公開ドキュメントから。
- [AEGIS auf Ubuntu installieren und eine Aufgabe freigeben](https://100monkeys.ai/blog/de/install-aegis-on-ubuntu-vps) (de): AEGIS mit einem Befehl auf einem Ubuntu-Server installieren, einen Agenten ausführen und sein Ergebnis hinter eine menschliche Freigabe stellen.
- [Installer AEGIS sur Ubuntu et lancer une tâche approuvée](https://100monkeys.ai/blog/fr/install-aegis-on-ubuntu-vps) (fr): Installez AEGIS sur un serveur Ubuntu en une commande, lancez un agent, puis placez son résultat derrière une approbation humaine. Tout vient de la doc.
- [Ubuntu에 AEGIS 설치하고 승인된 작업 실행하기](https://100monkeys.ai/blog/ko/install-aegis-on-ubuntu-vps) (ko): 명령 하나로 새 Ubuntu 서버에 AEGIS를 설치하고, 에이전트를 실행한 뒤 그 결과를 사람의 승인 뒤에 둡니다. 모든 단계는 공개 문서에서 가져왔습니다.
- [在 Ubuntu 上安装 AEGIS 并运行一个经批准的任务](https://100monkeys.ai/blog/zh/install-aegis-on-ubuntu-vps) (zh-Hans): 用一条命令在全新的 Ubuntu 服务器上安装 AEGIS,运行一个智能体,再把它的结果放在人工批准之后。每一步都来自公开文档。
- [Installare AEGIS su Ubuntu ed eseguire un task approvato](https://100monkeys.ai/blog/it/install-aegis-on-ubuntu-vps) (it): Installa AEGIS su un server Ubuntu con un comando, esegui un agente e metti il risultato dietro un'approvazione umana. Ogni passo dalla documentazione.
- [Ubuntu पर AEGIS इंस्टॉल करें और एक स्वीकृत टास्क चलाएँ](https://100monkeys.ai/blog/hi/install-aegis-on-ubuntu-vps) (hi): एक कमांड से नए Ubuntu सर्वर पर AEGIS इंस्टॉल करें, एक एजेंट चलाएँ, फिर उसके नतीजे को इंसानी स्वीकृति के पीछे रखें। हर चरण सार्वजनिक दस्तावेज़ों से।
- [A traceability checklist for AI agents in production](https://100monkeys.ai/blog/ai-agent-traceability-checklist): What to log on every agent run, what to sign so the log can be trusted, and what to show the reviewer. Vendor-neutral, with open standards for each step.
- [Lista de trazabilidad para agentes de IA en producción](https://100monkeys.ai/blog/es/ai-agent-traceability-checklist) (es): Qué registrar en cada ejecución de un agente, qué firmar para que el registro sea fiable y qué mostrar a quien revisa. Neutral, con estándares abiertos.
- [Checklist de rastreabilidade para agentes de IA](https://100monkeys.ai/blog/pt/ai-agent-traceability-checklist) (pt): O que registrar em cada execução de um agente, o que assinar para o registro ser confiável e o que mostrar a quem revisa. Neutro, com padrões abertos.
- [本番 AI エージェントのトレーサビリティ・チェックリスト](https://100monkeys.ai/blog/ja/ai-agent-traceability-checklist) (ja): エージェントの各実行で何を記録し、記録を信頼できるものにするために何に署名し、レビュー担当者に何を見せるか。特定ベンダーに依存せず、各項目にオープン標準を添えています。
- [Checkliste: Nachvollziehbarkeit von KI-Agenten](https://100monkeys.ai/blog/de/ai-agent-traceability-checklist) (de): Was Sie bei jedem Agentenlauf protokollieren, was Sie signieren, damit das Protokoll vertrauenswürdig ist, und was Prüfende sehen. Herstellerneutral.
- [Liste de traçabilité pour agents d'IA en production](https://100monkeys.ai/blog/fr/ai-agent-traceability-checklist) (fr): Quoi journaliser à chaque exécution d'un agent, quoi signer pour un journal fiable, quoi montrer à la personne qui relit. Neutre, standards ouverts.
- [운영 중인 AI 에이전트를 위한 추적성 체크리스트](https://100monkeys.ai/blog/ko/ai-agent-traceability-checklist) (ko): 에이전트 실행마다 무엇을 기록하고, 기록을 믿을 수 있게 무엇에 서명하고, 검토자에게 무엇을 보여 줄지. 특정 벤더에 묶이지 않고 단계마다 공개 표준을 씁니다.
- [生产环境中 AI 智能体的可追溯性清单](https://100monkeys.ai/blog/zh/ai-agent-traceability-checklist) (zh-Hans): 每次智能体运行要记录什么、为使记录可信要签名什么、要给审阅者看什么。不绑定厂商,每一步都对应开放标准。
- [Checklist di tracciabilità per agenti di IA in produzione](https://100monkeys.ai/blog/it/ai-agent-traceability-checklist) (it): Cosa registrare a ogni esecuzione di un agente, cosa firmare perché il log sia affidabile e cosa mostrare al revisore. Neutrale, con standard aperti.
- [प्रोडक्शन में AI एजेंटों के लिए ट्रेसबिलिटी चेकलिस्ट](https://100monkeys.ai/blog/hi/ai-agent-traceability-checklist) (hi): हर एजेंट रन में क्या दर्ज करें, लॉग पर भरोसा हो इसके लिए किस पर हस्ताक्षर करें, और समीक्षक को क्या दिखाएँ। हर चरण के लिए खुले मानक।
- [How to add an approval step to an agent orchestrator](https://100monkeys.ai/blog/approval-step-for-an-agent-orchestrator): A pattern for human approval gates in agent workflows: where the gate goes, what the reviewer sees, what silence means, with AEGIS as the worked example.
- [Cómo añadir un paso de aprobación a un orquestador](https://100monkeys.ai/blog/es/approval-step-for-an-agent-orchestrator) (es): Un patrón de aprobación humana en workflows de agentes: dónde va la compuerta, qué ve quien revisa, qué significa el silencio. Con AEGIS como ejemplo.
- [Como adicionar uma etapa de aprovação a um orquestrador](https://100monkeys.ai/blog/pt/approval-step-for-an-agent-orchestrator) (pt): Um padrão de aprovação humana em workflows de agentes: onde fica o portão, o que o revisor vê, o que o silêncio significa. Com o AEGIS como exemplo.
- [エージェント・オーケストレーターに承認ステップを加える方法](https://100monkeys.ai/blog/ja/approval-step-for-an-agent-orchestrator) (ja): エージェントのワークフローに人間の承認ゲートを置くためのパターン。ゲートの位置、レビュー担当者に見せるもの、無応答の意味を、AEGIS を例に説明します。
- [Einen Freigabeschritt in einen Orchestrator einbauen](https://100monkeys.ai/blog/de/approval-step-for-an-agent-orchestrator) (de): Ein Muster für menschliche Freigaben in Agenten-Workflows: wo das Gate sitzt, was Prüfende sehen, was Schweigen bedeutet. Mit AEGIS als Beispiel.
- [Ajouter une étape d'approbation à un orchestrateur](https://100monkeys.ai/blog/fr/approval-step-for-an-agent-orchestrator) (fr): Un modèle d'approbation humaine dans les workflows d'agents : où placer la porte, ce que voit qui relit, ce que vaut le silence. Exemple : AEGIS.

## Company

- [GitHub](https://github.com/100monkeys-ai): the 100monkeys-ai organization
- [LinkedIn](https://www.linkedin.com/company/112423436/): 100monkeys.ai
- [X](https://x.com/100monkeysai): @100monkeysai
- [Hashnode](https://100monkeys-ai.hashnode.dev): engineering articles