# Agensh

> A self-organized, decentralized multi-agent harness from Microsoft Research that scales to 1,024 agents without a central orchestrator.

Agensh is an open-source multi-agent harness from Microsoft Research in which concurrent agent workers gather context, claim sub-tasks, share findings, verify results and merge progress asynchronously, with no central orchestrator. The project's authors report evaluations scaling from 1 to 1,024 agents on ProgramBench tasks. The code is MIT-licensed, and the latest listed release is v1.1.

## What It Is

Agensh is a harness that defines a cooperation loop for many agents working on one shared goal, such as building out a software repository. Each worker proceeds independently and shares progress through a lightweight agentic organization infrastructure made up of a shared workspace, a message interface and shared context. Gitea provides the shared workspace, Mattermost provides messaging, and the shared context mechanism is adapted from DeLM.

## Backends and Setup

Agensh is layered on top of single-agent harnesses. Copilot is the default and was used for the 1.0 experiments, and Pi, Codex and Claude Code are also supported, selected with an `--agent-harness` option. The release includes a single-node team setup using Docker Compose and a standalone single-agent baseline. Users can also run a team on their own software repository, and the documentation includes a reproduction guide, harness configuration and launch scripts.

## Reported Scaling Results

The authors state that, with GPT-5.6-sol at high reasoning effort, a six-hour budget and no Internet access, mean final test-pass rate across the five hardest ProgramBench tasks rose from 19.31% with 1 agent to 28.78% with 128 agents. On Pandoc, they report 33.89% with 1 agent and 55.06% with 1,024 agents. They also report that peer coordination, integration workflows and specialized roles emerge as the organization grows. A replay demo of the 1,024-agent run is published on the project page.

## Features
- Decentralized multi-agent cooperation without a central orchestrator
- Asynchronous sub-task claiming, verification and merging
- Shared workspace via Gitea
- Messaging interface via Mattermost
- Shared context mechanism adapted from DeLM
- Selectable single-agent backends: Copilot, Codex, Claude Code, Pi
- Docker Compose single-node team setup
- Standalone single-agent baseline
- Launch scripts to run a team on your own software repository
- Replay demo of 1,024 agents cooperating

## Integrations
Gitea, Mattermost, GitHub Copilot CLI, OpenAI Codex, Claude Code, Pi, DeLM, Docker Compose

## Platforms
WINDOWS, LINUX, WEB, API, CLI

## Pricing
Open Source

## Version
v1.1

## Links
- Website: https://aka.ms/Agensh
- Documentation: https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md
- Repository: https://github.com/microsoft/Agensh
- EveryDev.ai: https://www.everydev.ai/tools/agensh