// agents · Nasiko-Labs/nasiko

nasiko

nasiko é um projeto de agentes de IA de código aberto de Nasiko-Labs (Nasiko-Labs/nasiko no GitHub). Tem 9.514 estrelas no GitHub e 2.064 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 7 de outubro de 2026.

The open runtime for AI agents — a Rust platform for running, governing and routing agents with TokenOps.

★ 9,5 mil estrelas⑂ 2,1 mil forksApache-2.0atualizado out 2026

Ver no GitHub ↗Official site ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: Nasiko-Labs/nasiko
Estrelas no GitHub: 9.514
Forks: 2.064
Licença: Apache-2.0
Última atualização no GitHub: 7 de outubro de 2026
Categoria: Agentes de IA
Tipo de ficha: Guia de instalação completo
Site oficial: Official site

// como funciona

Como funciona

Clarify your goal
Decide whether you want the Docker-only platform path or the Rust CLI path, and which agents and LLM providers the runtime should manage.
Get the project
Clone Nasiko-Labs/nasiko from GitHub (or use the install path in the run steps below) and skim its README for the parts relevant to your goal.
Install and configure
Clone the repo, copy and edit the environment configuration, then start the platform with Docker Compose — no Rust needed for this path.
Run your first task
Open the running platform, check what agents are already running, connect one agent or harness, and watch its session and token usage appear.

// recursos

Por que as pessoas gostam tanto

Agent runtime and orchestration

Runs agents as containers under a Docker runtime, with orchestration for multi-agent setups rather than single scripts.

TokenOps

Token-level visibility and management for agent workloads, surfaced as a first-class part of the runtime.

Policy, security and governance

A dedicated policy and governance layer for controlling what agents may do inside the runtime.

Model routing for harnesses

Coding agents can report sessions to Nasiko and hand the model choice back to its routing, instead of hard-coding a model.

LLM config management

Central management of LLM configuration for the agents the runtime hosts, editable via the server environment.

MCP gateway

Exposes an MCP gateway so agents can reach tools through a governed runtime endpoint.

// execute você mesmo

Execute você mesmo

Clone the repository
Get the source from the official GitHub repository for nasiko.
```
git clone https://github.com/Nasiko-Labs/nasiko.git
cd nasiko
```
Start the platform with Docker
After cloning and editing .env, start everything with Docker Compose as the README's quick start shows.
```
docker compose up -d
```
Or install the CLI from source
With a Rust toolchain installed, build and install the Nasiko CLI from the cloned repo.
```
cargo install --path cli/ --force
```

// casos de uso

O que você pode criar

Running several internal agents in containers with central token and policy visibility
Giving coding-agent harnesses a shared place to report sessions and route model choice
Governing which tools agents can reach through an MCP gateway
Self-hosting an agent platform instead of sending workloads to a hosted runtime

// perguntas frequentes

Perguntas frequentes

Who maintains nasiko?

Nasiko-Labs, through the Nasiko-Labs/nasiko repository, with the product site at nasiko.com.

Is nasiko free to use?

Yes — the project is open source under the Apache-2.0 license as recorded for this listing. See the license terms for any conditions on redistribution.

Does nasiko need a paid API key?

Agents you run will use LLM providers you configure, with your own keys and provider billing; the Nasiko runtime itself is open source under Apache-2.0.

How does Nasiko compare to an agent framework like a Python SDK?

A framework helps you write one agent in code. Nasiko is a runtime for operating agents — containers, routing, session reporting, TokenOps and governance — so it complements frameworks rather than replacing the code you write.

How do I get started with nasiko?

Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se nasiko não for o ideal para você.

openclaw★ 391,6 mil
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 mil
An agentic skills framework & software development methodology that works.
ECC★ 275,2 mil
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 mil
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 mil
DeepSeek's plugin-based agent harness where everything is a plugin.

// mais em agents

Mais em Agentes de IA

Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de nasiko: continue explorando dos dois lados dele.

mobilerun★ 9,6 mil
Control Android and iOS devices with natural language — an LLM-agnostic mobile agent framework and CLI.
garak★ 9,5 mil
Scan your LLM for vulnerabilities before attackers do.
UFO★ 10,0 mil
Microsoft's GUI agent that grew into UFO³ — orchestrating agents across Windows, Linux and mobile devices.
MobileAgent★ 9,3 mil
Mobile-Agent — multimodal GUI agents that operate phones and PCs from screenshots and instructions.
apify-mcp-server★ 10,1 mil
MCP server that lets AI agents run thousands of Apify Store scrapers and crawlers as tools.
local-deep-research★ 9,2 mil
Deep research that stays on your machine — local or cloud LLMs, 10+ search engines, encrypted and private.

Baixe o nasiko

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de Agentes de IA