AI Agents
commonly
Shared rooms where humans and cross-vendor AI agents work together.
★ 1.4k starsApache-2.0
View guide →// agents · Twigpine/zero
zero
zero is an open-source ai agents project by Twigpine (Twigpine/zero on GitHub). It has 1,695 GitHub stars and 194 forks, is released under the MIT license, and was last updated on GitHub on 28 September 2026.
A coding agent that runs on your model, your machine, your rules.
💎 Hidden gem★ 1.7k stars⑂ 194 forksMITupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- Twigpine/zero
- GitHub stars
- 1,695
- Forks
- 194
- License
- MIT
- Last updated on GitHub
- 28 September 2026
- Category
- AI Agents
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Clone the repository
Download the source and enter the folder.
- Build the agent
Compile the Go binary.
- Configure your model
Add your provider API key per the README.
- Start coding
Launch zero in your project directory.
// features
Why people love it
Your model choice
Works with Anthropic, Gemini, and more.
Your machine
Runs locally under your control.
Your rules
Behavior configured by you, not a vendor.
MCP support
Extends through the Model Context Protocol.
Go CLI
Fast single binary, no runtime to install.
1,695 stars
Wide community adoption.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/Twigpine/zero.git cd zero - Step 2 — Build the agent
Compile the Go binary.
go build ./... - Step 3 — Launch it
Start zero in your project after configuring a key.
./zero
// use cases
What you can build
- Code with your preferred model, not a default.
- Keep agent work on your own machine.
- Extend the agent via MCP tools.
- Run agentic coding without vendor lock-in.
Advertisement
// faq
Questions, answered
Who maintains zero?
It is an open-source project at Twigpine/zero with 194 forks.
Is it free for commercial use?
Yes. It is MIT licensed.
Which models does it support?
Anthropic, Gemini, and others — you bring your own API key.
Do I need the cloud?
No. It runs on your machine under your rules.
Can I extend it?
Yes. It supports MCP for adding tools.
// keep exploring
Similar tools
AI Agents
LongHorizon-Harness
Run AI agents on desktop apps and CLI for hours without losing state.
★ 1.7k starsMIT
View guide →Local LLM
agent-console
Local-first dashboard of tokens, models, and cost for coding agents.
★ 800 starsMIT
View guide →AI Agents
openclaude
A Claude Code-style coding agent that runs anywhere and works with almost any model provider
★ 33.7k starsMIT
View guide →Agents
bernstein
Governance and orchestration for AI agent fleets: declarative rules, verifiable runs.
★ 1.4k starsApache-2.0
View guide →Agents
ruler
Write coding-agent rules once, then apply them to every AI coding tool you use.
★ 2.9k starsMIT
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if zero is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to zero — keep exploring the shelf either side of it.
- zerostack★ 1.7k
Lean coding agent written in Rust, optimized for memory footprint and performance.
- CyberVerse★ 1.7k
Self hosted, live digital human agent system.
- langmem★ 1.7k
LangMem: long-term memory primitives for LangGraph agents that learn and adapt from conversations.
- Swift-Concurrency-Agent-Skill★ 1.7k
Give your AI coding tool expert Swift Concurrency guidance.
- adk-java★ 1.7k
A code-first Java toolkit for building AI agents.
- spec-kitty★ 1.7k
Open ai agents for spec-driven development with organizational governance..
Get zero
Free and open — grab the source, star the repo, and start creating.