Openai Agents Python
A lightweight, powerful framework for multi-agent workflows
10x is an open-source agents project by ntegrals (ntegrals/10x on GitHub). It has 1,366 GitHub stars and 112 forks, is released under the MIT license, and was last updated on GitHub on 5 January 2026.
Up to 20x faster AI coding with smart model routing and full self-hosting.
Set up the agent.
Bring your own model keys.
Smart routing picks models per step.
Run everything on your infrastructure.
The right model for each step.
Complex tasks, handled fast.
Your keys, your bills.
Full control of infrastructure.
MIT licensed.
Latency treated as a feature.
Download the source and move into the project folder.
git clone https://github.com/ntegrals/10x.git
cd 10xEvery project documents its own setup; start with install requirements.
cat README.md | head -60Follow the project’s launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch commandIt is an open-source project at ntegrals/10x with 112 forks.
Yes. MIT licensed.
That is the project’s claim; your mileage will vary.
Your configured providers; check the docs.
A machine plus your own model API keys.
A lightweight, powerful framework for multi-agent workflows
An agentic skills framework & software development methodology that works.
Community-built terminal coding agent: bring your own model, keep code local.
Self-managing, unbounded context and long-term memory for coding agents: one session, for life.
Beam — Reflection's open 501B MoE model built for agentic coding: 23B active parameters, a 1M-token context, Apache-2.0 weights, and Mirror, its open-source terminal harness
A self-improving agent for coding workflows and long-running autonomous tasks
The most-starred other Agents projects in the LibreAI catalogue — the realistic shortlist if 10x is not the right fit.
A personal AI that really does things — on any OS, with your data staying yours.
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
DeepSeek's plugin-based agent harness where everything is a plugin.
Nearby Agents projects in the catalogue, closest in stars to 10x — keep exploring the shelf either side of it.
Nocturne_memory, in Python — built for a lightweight, rollbackable, and visual long-ter...
Shared rooms where humans and cross-vendor AI agents work together.
Orchestrate Claude Code, Kiro, and Codex together in isolated tmux sessions.
Run poco-claw locally: a more beautiful and easier-to-use alternative to openc.
Parallel multi-agent research that compiles wikis from any topic.
C99+ style guide with an AI agent skill for formatting code.
Free and open — grab the source, star the repo, and start creating.