Ross ROSS = Recommend OSS · open-source software intelligence for agents

MiniMax-AI/Mini-Agent

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents. observed · 2026-08-28

github.com/MiniMax-AI/Mini-Agent · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

47/100

  • Activity 67
  • Release rhythm 35
  • Longevity 21

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 306
  • days_rel: n/a
  • days_push: 200
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2984 stars · 439 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A minimal yet professional Python demo project showcasing best practices for building a single LLM agent on the MiniMax M2.5 model via an Anthropic-compatible API. It implements a full agent execution loop with file/shell tools, persistent session memory, automatic context summarization, Claude Skills, and MCP tool integration behind a clean CLI.

Use cases

  • build an AI agent with MiniMax M2.5
  • learn how agent execution loops work
  • run an agent that edits files and runs shell commands
  • give an agent persistent memory across sessions
  • handle long tasks with automatic context summarization
  • integrate MCP tools like web search into an agent
  • starting point for building custom coding agents

When to choose

  • you want a small, readable codebase to learn agent architecture
  • you are building on MiniMax models and want a reference implementation
  • you need a working CLI agent with memory, skills, and MCP support out of the box

When to avoid

  • you need a production multi-agent orchestration framework
  • you require model-agnostic support beyond Anthropic-compatible APIs
  • you want a GUI or web-based agent interface

Facets

application · maturity active

agent-framework llm-inference mcp cli developer-tools large-language-models developer-tools python cli cross-platform minimax single-agent claude-skills session-memory context-management demo-project ai-agents command-line

7 sources

Member repositories

RepositoryRoleHealth v2
MiniMax-AI/Mini-Agentmain47

For agents

markdown · JSON · MCP: product_card(name="MiniMax-AI/Mini-Agent")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem