# mpaepper/llm_agents

Build agents which are controlled by LLMs

Repository: https://github.com/mpaepper/llm_agents
Canonical: https://ross.abutalabs.com/products/llm_agents
Homepage: https://www.paepper.com/blog/posts/intelligent-agents-guided-by-llms/
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, langchain, llms, machine-learning
Last push: 2025-06-23T14:01:18+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 28, release rhythm 35, longevity 89
- inputs: {"age_days": 1247, "days_push": 436, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1053, forks 85 (observed 2026-08-28T04:03:23.576256+00:00)

## What it is
A small Python library for building agents controlled by large language models, inspired by LangChain but implemented from scratch in very few lines of code. It runs a ReAct-style loop of Thought, Action, and Observation, using tools like a Python REPL, Google search, and Hacker News search.

## Use cases
- build llm-controlled agents
- understand how langchain agents work internally
- run a reAct agent loop with custom tools
- let an llm execute python code and search the web
- minimal agent framework for learning
- implement custom tools for an llm agent

## When to choose
- you want to learn how LLM agents work with minimal abstraction
- you need a tiny, readable ReAct agent implementation to extend
- langchain feels too heavy for a simple agent experiment

## When to avoid
- you need production-grade agent features, memory, or many integrations
- you want a maintained framework with broad tool ecosystem
- you need multi-agent orchestration or streaming

## Facets
- artifact type: library
- maturity: maintenance
- function: agent-framework, llm-inference, prompt-engineering
- domain: artificial-intelligence, large-language-models, machine-learning
- platform: python, cli
- tags: llm-agents, tool-use, react, langchain-alternative, educational, openai, ai-agents

## Member repositories
- mpaepper/llm_agents (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.576256+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:59:22.470909+00:00, confidence not recorded.
  - readme: https://github.com/mpaepper/llm_agents (fetched 2026-08-28T04:03:23.576256+00:00, sha 405a1612c2c8)
  - homepage: https://www.paepper.com/blog/posts/intelligent-agents-guided-by-llms/ (fetched 2026-08-29T13:01:05.796783+00:00, sha bf86fb59b5b2)
  - registry_pypi: https://pypi.org/pypi/llm_agents/json (fetched 2026-08-29T13:01:05.818629+00:00, sha 1fd3aef5ba4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.