Skip to main content

A building block library for composed agent workflows

Project description

agenticblocks 🧱

A composable building block library for AI agent workflows. / Uma biblioteca componível para construir fluxos de agentes de IA.

🇺🇸 English | 🇧🇷 Português


🇺🇸 English

Philosophy

A library to build agent workflows like Lego blocks. Each step in your agentic pipeline is a self-contained block, with strictly typed inputs and outputs via Pydantic and natively concurrent execution using AsyncIO and NetworkX graphs.

  • Strong typing: Pydantic validates connections and prevents unmatched dependencies between LLM tool calls.
  • Standardized connections: Blocks only know their own inputs and outputs. Thus, entire workflows can act as single blocks later.
  • Smart Parallelism (Waves): The asyncio engine fires simultaneous tasks (waves) whenever dependencies are resolved, maximizing API speed.
  • Native Cycles: Declare bounded feedback loops directly in the graph (add_cycle()). The executor handles iteration, feedback propagation, and exit conditions automatically.
  • Functions as Tools: Any plain Python function (sync or async) becomes a block with @as_tool — no class boilerplate required.
  • Focus on local open-source models: small models run well with this library, as we provide ready-made blocks that handle their limitations, such as HeuristicLLMAgentBlock, which heuristically extracts tool calls in JSON format from plain text and executes them transparently. See more in docs/heuristicagent.md.

Getting Started

Install the latest release:

pip install agenticblocks.io

Or for local development:

pip install -e .

1. Define Input and Output Models

from pydantic import BaseModel

class HelloInput(BaseModel):
    name: str

class HelloOutput(BaseModel):
    greeting: str

2. Create the Logic Block

from agenticblocks.core.block import Block

class HelloWorldBlock(Block[HelloInput, HelloOutput]):
    name: str = "say_hello"
    
    async def run(self, input: HelloInput) -> HelloOutput:
        msg = f"Hello, {input.name}! Welcome to agenticblocks."
        return HelloOutput(greeting=msg)

3. Connect and Execute

import asyncio
from agenticblocks.core.graph import WorkflowGraph
from agenticblocks.runtime.executor import WorkflowExecutor

async def main():
    graph = WorkflowGraph()
    graph.add_block(HelloWorldBlock(name="say_hello"))

    executor = WorkflowExecutor(graph)
    ctx = await executor.run(initial_input={"name": "Alice"})
    
    print(ctx.get_output("say_hello").greeting)

asyncio.run(main())

4. Functions as Tools

Any Python function can be registered as a block with @as_tool. Both sync and async functions are supported — sync functions run in a thread pool automatically.

from agenticblocks import as_tool
from agenticblocks.blocks.llm.agent import LLMAgentBlock

@as_tool
async def fetch_weather(city: str) -> str:
    """Returns the current weather for a city."""
    return f"Sunny in {city}."

agent = LLMAgentBlock(
    name="assistant",
    model="gpt-4o-mini",
    tools=[fetch_weather],   # same interface as any Block
)

5. LLM Agent Autonomy & A2A

LLMAgentBlock is a ready-to-use orchestrator that dynamically translates your other Blocks into Tools (Agent-to-Agent) seamlessly.

  • Bounded tool loop: max_tool_calls prevents runaway loops.
  • A2A bridging: sub-agents are called as tools transparently — the parent LLM receives only the text response, not raw JSON metadata.
  • Connection Pooling: Pass any litellm_kwargs (HTTP clients, timeouts, etc.) to optimize API performance.
  • Iteration Hooks: Use the on_iteration parameter to inject callbacks that execute at the beginning of each loop iteration. These callbacks receive the current iteration number and the list of messages, allowing for real-time monitoring, logging, or dynamic prompt adjustments during the agent's execution.

6. Advanced Flow Control & Heuristics

  • PromptBuilderBlock: Merges outputs from multiple predecessors into a single formatted AgentInput prompt using Python format-strings. Useful for "diamond" graph patterns (e.g., feeding both the original topic and a search report to a final summarizer).
  • HeuristicLLMAgentBlock: A specialized agent for models with weak native tool support (like smaller local models). It heuristically parses hallucinated JSON tool calls out of plain text responses and executes them transparently.

7. Native Feedback Cycles

Declare validator loops directly in the graph without any wrapper block:

from agenticblocks import as_tool
from agenticblocks.core.graph import WorkflowGraph
from agenticblocks.blocks.llm.agent import LLMAgentBlock

writer = LLMAgentBlock(
    name="writer",
    model="gpt-4o-mini",
    system_prompt="Write a detailed essay about AI."
)

@as_tool
def validate_output(content: str) -> dict:
    ok = len(content.split()) >= 100
    return {"is_valid": ok, "feedback": "Too short." if not ok else ""}

graph = WorkflowGraph()
graph.add_block(writer)
graph.add_block(validate_output)

graph.add_cycle(
    name="refine",
    edges=[("writer", "validate_output")],
    condition_block="validate_output",
    max_iterations=3,
)
# Downstream nodes connect to the cycle output as a normal node
graph.connect("refine", "publisher")

The executor runs the cycle, propagates feedback to the producer on each rejection, and stores the result in ctx under the cycle name.

8. Code-Generation Planning

AgenticBlocks supports dynamic code execution out-of-the-box. Instead of relying on predefined tools, you can use the CodePlanExecutorBlock to orchestrate an LLM that generates a standalone Python script to solve a problem. The generated code is automatically executed either locally or securely in an ephemeral Docker container via the PythonCodeExecutorBlock. See more in docs/codeplanner.md.

Examples & Model Recommendations

It is recommended to install Ollama with the model granite4:1b (ollama run granite4:1b) to test the examples locally. Alternatively, you can modify the examples to use a commercial API, such as Gemini (gemini/gemini-2.0-flash) or OpenAI.

Example Description
01_hello_world.py Minimal block + graph + executor setup
02_llm_pipeline.py Parallel wave execution with multiple blocks
03_mcp_a2a_agent.py MCP bridge + Agent-to-Agent (A2A) tool delegation
04_mcp_python_native.py Native Python MCP server
05_basic_blocks.py Overhead benchmarking
06_functionastool.py @as_tool decorator for plain functions
07_validator_loop.py Native graph cycle with producer + validator feedback loop
08_planner.py JSON Plan-and-Execute pattern
09_code_planner_local.py Code-Generation Planner running locally
10_code_planner_docker.py Code-Generation Planner running inside a Docker sandbox

Note: Quantized or small models like granite may produce lower-quality reasoning and struggle with native tool calling. For reliable local tool usage, use llama3.1 or mistral-nemo. If using granite4, prefer the HeuristicLLMAgentBlock to capture hallucinated JSON tool calls. Large commercial models (OpenAI, Gemini, Anthropic) yield excellent results but require an API key.


🇧🇷 Português

Filosofia

Uma biblioteca para construir fluxos de agentes no estilo Lego. Cada passo do seu pipeline agêntico é um bloco auto-contido, com entradas e saídas rigorosamente tipadas via Pydantic e execução simultânea usando AsyncIO e grafos do NetworkX.

  • Forte tipagem: Pydantic valida os encaixes e previne dependências não satisfeitas.
  • Encaixes padronizados: Blocos só conhecem as próprias entradas e saídas. Workflows inteiros funcionam como blocos únicos.
  • Paralelismo Inteligente (Ondas): O motor dispara tarefas simultâneas sempre que as dependências de um bloco são resolvidas.
  • Ciclos Nativos: Declare loops de feedback diretamente no grafo com add_cycle(). O executor gerencia iteração, propagação de feedback e condição de saída automaticamente.
  • Funções como Ferramentas: Qualquer função Python (síncrona ou async) vira um bloco com @as_tool — sem boilerplate de classe.
  • Foco em modelos locais open-source: modelos pequenos rodam bem com esta biblioteca, pois provemos blocos prontos que lidam com suas limitações, como HeuristicLLMAgentBlock, que extrai heuristicamente chamadas de ferramenta em formato JSON do texto plano e as executa de forma transparente. Veja mais em docs/heuristicagent.md.

Primeiros Passos

Instale o último lançamento:

pip install agenticblocks.io

Ou para desenvolvimento local:

pip install -e .

1–3. Blocos, Grafo e Execução

A estrutura básica é idêntica ao tutorial acima (seção em inglês): defina modelos Pydantic, crie um Block, adicione ao WorkflowGraph e execute com WorkflowExecutor.

4. Funções como Ferramentas

Qualquer função pode ser registrada como bloco com @as_tool. Funções síncronas rodam em thread pool automaticamente.

from agenticblocks import as_tool

@as_tool
def buscar_clima(cidade: str) -> str:
    """Retorna o clima atual de uma cidade."""
    return f"Ensolarado em {cidade}."

5. Autonomia com Agentes LLM & A2A

O LLMAgentBlock abstrai e converte sub-blocos em ferramentas nativas (A2A). Destaques:

  • max_tool_calls: Limita o loop de ferramentas para evitar execuções infinitas.
  • A2A transparente: Agentes subordinados são chamados como ferramentas; o agente pai recebe apenas o texto da resposta, sem metadados JSON brutos.
  • Connection Pooling: Aceite sessões HTTP e parâmetros estendidos via litellm_kwargs.

6. Controle de Fluxo Avançado & Heurísticas

  • PromptBuilderBlock: Mescla saídas de múltiplos predecessores em um único prompt AgentInput formatado. Ideal para padrões de grafo em "diamante".
  • HeuristicLLMAgentBlock: Agente especializado para modelos com suporte fraco a chamadas de ferramentas (como modelos locais pequenos). Ele extrai heuristicamente chamadas de ferramenta em formato JSON do texto plano e as executa de forma transparente.
  • Callbacks de Iteração (on_iteration): Use o parâmetro on_iteration para injetar funções de callback que serão executadas no início de cada iteração do loop do agente. Isso permite monitoramento em tempo real, logging ou ajustes dinâmicos no prompt durante a execução do agente.

7. Ciclos de Feedback Nativos

Declare um loop validador diretamente no grafo — sem bloco orquestrador especial:

from agenticblocks import as_tool
from agenticblocks.core.graph import WorkflowGraph
from agenticblocks.blocks.llm.agent import LLMAgentBlock

escritor = LLMAgentBlock(
    name="escritor",
    model="gpt-4o-mini",
    system_prompt="Escreva uma redação detalhada sobre IA."
)

@as_tool
def validar(content: str) -> dict:
    ok = len(content.split()) >= 100
    return {"is_valid": ok, "feedback": "Muito curto." if not ok else ""}

graph = WorkflowGraph()
graph.add_block(escritor)
graph.add_block(validar)

graph.add_cycle(
    name="refinar",
    edges=[("escritor", "validar")],
    condition_block="validar",
    max_iterations=3,
)
graph.connect("refinar", "publicador")

O executor itera automaticamente, injeta o feedback no prompt do produtor a cada rejeição e disponibiliza o resultado final em ctx.get_output("refinar").

8. Planejamento Baseado em Geração de Código

O AgenticBlocks oferece suporte a execução dinâmica de código nativamente. Em vez de depender de ferramentas pré-definidas, você pode usar o CodePlanExecutorBlock para orquestrar um LLM na geração de um script Python completo capaz de resolver um problema. O código gerado é então testado e executado automaticamente no modo local ou de forma segura isolado em um contêiner Docker via PythonCodeExecutorBlock. Veja mais em docs/codeplanner.md.

Exemplos & Modelos

Recomenda-se instalar o Ollama com o modelo granite4:1b para testar localmente. Alternativamente, use uma API comercial como Gemini ou OpenAI.

Exemplo Descrição
01_hello_world.py Setup mínimo: bloco + grafo + executor
02_llm_pipeline.py Execução paralela em waves
03_mcp_a2a_agent.py Bridge MCP + delegação A2A entre agentes
04_mcp_python_native.py Servidor MCP nativo em Python
05_basic_blocks.py Benchmark de overhead
06_functionastool.py Decorator @as_tool para funções simples
07_validator_loop.py Ciclo nativo no grafo: produtor + validador com feedback
08_planner.py Padrão JSON Plan-and-Execute
09_code_planner_local.py Planejador via Geração de Código (ambiente Local)
10_code_planner_docker.py Planejador via Geração de Código (Sandbox Docker)

Atenção: Modelos quantizados ou menores podem produzir resultados abaixo do esperado e ter dificuldade com chamadas nativas de ferramentas. Para uso local confiável de ferramentas, prefira llama3.1 ou mistral-nemo. Caso use granite4, utilize o HeuristicLLMAgentBlock. Modelos comerciais grandes geram excelentes resultados, mas exigem configuração de API KEY.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agenticblocks_io-0.8.18.tar.gz (31.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agenticblocks_io-0.8.18-py3-none-any.whl (39.5 kB view details)

Uploaded Python 3

File details

Details for the file agenticblocks_io-0.8.18.tar.gz.

File metadata

  • Download URL: agenticblocks_io-0.8.18.tar.gz
  • Upload date:
  • Size: 31.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for agenticblocks_io-0.8.18.tar.gz
Algorithm Hash digest
SHA256 c00c8cc252967f573fec8f0b86f97ae52300fa0d4f2857281b11c7bc857a7b0e
MD5 e2b656ef664c783294535a5b49ad2b87
BLAKE2b-256 32ec2ef63aae911a4440226bb2f6b388d2e9b112ff2bf9d211facf84d97eec6f

See more details on using hashes here.

Provenance

The following attestation bundles were made for agenticblocks_io-0.8.18.tar.gz:

Publisher: workflow.yml on gilzamir18/agenticblocks

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file agenticblocks_io-0.8.18-py3-none-any.whl.

File metadata

File hashes

Hashes for agenticblocks_io-0.8.18-py3-none-any.whl
Algorithm Hash digest
SHA256 d77985886198b31afe63c18065228e24d05bcc178ce34c0a826fb43adcc5970e
MD5 206484928a9b7b0db384b8fce349c225
BLAKE2b-256 ba766f1dbb3727c8d8ad2ae8affffb0ce6c95c3f425b03b34eb70212e10124b9

See more details on using hashes here.

Provenance

The following attestation bundles were made for agenticblocks_io-0.8.18-py3-none-any.whl:

Publisher: workflow.yml on gilzamir18/agenticblocks

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page