PicoFlow
Tiny Python DSL for building LLM agent workflows
PicoFlow launched on January 22, 2026 with 1 votes.
What it does
PicoFlow is a small Python library for composing LLM agent workflows using a lightweight DSL. It lets you build multi-step agents with normal async functions and simple operators, without graph builders or complex configuration layers.
Simple, Flexible AI Agent Framework. Contribute to the-picoflow/picoflow development by creating an account on GitHub.
Build agents with explicit steps and a small DSL. LLMs, tools, loops, and branches compose naturally. from picoflow import flow , llm , create_agent LLM_URL = "llm+openai:///gpt-4.1-mini?api_key_env=OPENAI_API_KEY" @ flow async def mem ( ctx ): return ctx . add_memory ( "user" , ctx . input ) agent = create_agent ( mem >> llm ( "Answer in one sentence: {input}" , llm_adapter = LLM_URL ) ) print ( agent . get_output ( "What is PicoFlow?" , trace = True )) export OPENAI_API_KEY=sk-... python minimal.py Core Ideas Flow = step A flow is just a Python function that takes and returns State . DSL = pipeline Use >> to compose steps into readable execution graphs. Agent = runner create_agent(flow)…from github.com
Does a similar job
all alternatives →- PAPicoFlow – a tiny DSL-style Python library for LLM agent workflowsJan 2026 · ▲11
Hi HN, I’m experimenting with a small Python library called PicoFlow for building LLM agent workflows using a lightweight DSL. I’ve been using tools like LangChain and CrewAI, and wanted to explore a simpler, more function-oriented way to compose agent logic, closer to normal Python control flow and async functions. PicoFlow focuses on: - composing async functions with operators - minimal core and few concepts to learn - explicit data flow through a shared context - easy embedding into existing services A typical flow looks like: flow = plan >> retrieve >> answer await flow(ctx) Patterns…
Pipelex – Declarative language for repeatable AI workflowsOct 2025 · github.com · ▲122We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them. Why this instead of yet another workflow builder? - Declarative, not glue code: you state what to do; the runtime figures out how. - Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand. - Open…
Bloop – Answer questions about your code with an LLM agent2023 · github.com · ▲118Hi HN! We launched bloop 10 weeks ago (https://news.ycombinator.com/item?id=35236275) and received a huge amount of feedback (both positive + constructive). We've undertaken a rewrite of the core search framework, which now acts as an LLM agent, significantly improving the number of queries that can be successfully answered. There's a bunch of hype surrounding LLM agents, but we're positive this is one of the first implementations of an agent that can deliver immediate value for engineers working on existing projects, especially larger ones. We'll do a full write up of how the…
AdalFlow: The library to build and auto-optimize any LLM task pipeline2024 · github.com · ▲44AdalFlow: The library to build & auto-optimize LLM applications. - SylphAI-Inc/AdalFlow
Marvin – build AI functions that use an LLM as a runtime2023 · github.com · ▲127Hey HN! We're excited to share our new open-source project, Marvin. Marvin is a high-level library for building AI-powered software. We developed it to address the challenges of integrating LLMs into more traditional applications. One of the biggest issues is the fact that LLMs only deal with strings (and conversational strings at that), so using them to process structured data is especially difficult. Marvin introduces a new concept called AI Functions. These look and feel just like regular Python functions: you provide typed inputs, outputs, and docstrings. However, instead of relying on…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
