This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
What I Built
Most developer setups force engineers to choose a single coding assistant harness or manually copy-paste context between different agentic environments.
Multiharness solves this fragmentation. It is an open-source multi-agent orchestration framework written in Go designed to delegate tasks, manage iterative review loops, and coordinate coding sessions seamlessly across environments like Codex, OpenCode, and local LLM backends.
- The Problem: Single-agent harnesses often get stuck in local optima, struggle with verification loops without consuming massive context windows, and create lock-in around closed ecosystems.
- Who Itโs For & Why They'd Pay: Engineering teams, technical founders, and freelance developers looking to automate complex refactoring, test-generation pipelines, and cross-model code review loops without being tied to a single proprietary vendor or incurring massive API markups.
Demo
- Documentation & Overview: multiharness.mdfahimhossen.space
- CLI in Action: Run delegator and reviewer agents side-by-side with automatic state syncing across sessions.
Code
Multiharness is fully open-source. Explore the architecture, inspect agent harnesses, or contribute:
ErOr-0
/
Multiharness-Core
Multiharness Core is a Go command-line tool that connects AI coding agents so one can plan and review work while another implements it.
Multiharness Core: harness-bridge
One coding agent plans and reviews; another writes the code. For example
Claude Code plans, Codex CLI implements, and Claude Code reviews the result
harness-bridge connects the two. Any supported pairing works.
Contents
Get started
- Install: one line, then three questions
- Use it: what you do after setup
- Turning it off: disconnect or uninstall
Reference
- How it works: the MCP server and its five tools
- Supported agents: which agents can plan and implement
- Routing with Jev or Laya: skip planning for small requests
- Command line: the same tools from a shell
- What it does not enforce
Contribute
- Development: checks, project layout, building from source
- Releasing
Install
Windows (PowerShell):
irm https://raw.githubusercontent.com/ErOr-0/Multiharness-Core/main/install.ps1 | iex
macOS or Linux:
curl -fsSL https://raw.githubusercontent.com/ErOr-0/Multiharness-Core/main/install.sh | sh
The script downloads theโฆ
How I Built It
Multiharness is built with performance and composability at its core:
- Engineered in Go: Selected for low-latency concurrency, deterministic process management, and native cross-platform binaries with zero external runtime dependencies.
- Open-Source AI & Local Inference: Multiharness supports self-hosted open-weight models (via vLLM and Ollama) alongside open harnesses like OpenCode. It routes architecture, implementation, and test-review roles across specialized models depending on context window and reasoning requirements.
- Delegation & Review Loops: Uses structured task state machines where lead agents break down feature requests into atomic diffs, dispatch them to worker agents, and trigger automatic linting and test validation stages before merge proposals.
Why Does Open Innovation Matter?
Open innovation is critical when building developer tooling:
- Avoiding Vendor Lock-In: Developers should not be trapped within a single closed harness API that changes pricing, rate limits, or deprecates models overnight.
- Context Privacy & Local Execution: Engineering teams often handle sensitive codebases that cannot leave internal infrastructure. Open-weight models and open agent harnesses allow Multiharness to execute entirely on-prem or on developer workstations.
- True Modularity: Open architectures let developers plug in customized prompt templates, custom evaluation harnesses, and distinct model weights tailored for specific languages and domain logic.
Prize Categories
- Hacktoberfest Open-Source AI Challenge: Week 2 Side Hustle
Top comments (0)