{"version":1,"type":"story","url":"https://digestai.news/story/microsoft-open-sources-agensh-a-multi-agent-harness-for-coding","json":"https://digestai.news/story/microsoft-open-sources-agensh-a-multi-agent-harness-for-coding.json","markdown":"https://digestai.news/story/microsoft-open-sources-agensh-a-multi-agent-harness-for-coding.md","slug":"microsoft-open-sources-agensh-a-multi-agent-harness-for-coding","headline":"Microsoft Open-Sources Agensh, a Multi-Agent harness for coding","summary":"Microsoft Research has released Agensh, an open-source framework that allows large teams of coding agents to work together without a central manager. Unlike traditional orchestrator-worker models, Agensh lets each agent independently claim sub-tasks, share findings, and merge code into a shared Git repository. The system uses Gitea for version control, Mattermost for communication, and a shared context board to store typed notes.\n\nThe team tested the harness on the five hardest tasks from ProgramBench, scaling from one agent up to 1,024 agents. Results showed that increasing the number of agents generally improved performance and speed. With GPT-5.6-sol, the mean test-pass rate rose from 19.31% with one agent to 28.78% with 128 agents. On the pandoc task specifically, 1,024 agents achieved a 55.06% pass rate. The README also cites newer results using GPT-6.1-sol, where 32 agents reached a 79.59% pass rate on pandoc, though these figures are not included in the initial research paper.\n\nAgensh is designed to run on Linux using Docker Compose. The default setup supports eight workers on a single node, while the 1,024-agent test required 16 nodes. The code is available under an MIT license, but the team did not disclose the token costs associated with running such large-scale agent swarms.","keyPoints":["Microsoft Research open-sourced Agensh, a decentralized harness for coordinating up to 1,024 coding agents.","Tests on ProgramBench showed 128 agents raised the mean pass rate from 19.31% to 28.78% using GPT-5.6-sol.","The system uses Gitea, Mattermost, and a shared context board to allow agents to self-claim tasks and merge code."],"whyItMatters":"Agensh offers a scalable alternative to centralized agent orchestration, potentially enabling more efficient parallel coding tasks. Its open-source nature allows developers to experiment with large-scale agent cooperation without proprietary constraints.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["Microsoft Research"],"models":["GPT-5.6-sol","GPT-6.1-sol"],"people":[]},"firstPublishedAt":"2026-10-25T03:32:59Z","updatedAt":"2026-10-25T03:32:59Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Microsoft Open-Sources Agensh: A Multi-Agent Harness for 1,024 Agents","url":"https://marktechpost.com/2026/10/24/microsoft-agensh-multi-agent-harness-1024-agents","publishedAt":"2026-10-25T03:32:59Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Microsoft Open-Sources Agensh, a Multi-Agent harness for coding\", 25 October 2026, https://digestai.news/story/microsoft-open-sources-agensh-a-multi-agent-harness-for-coding","publisher":"Digest AI","title":"Microsoft Open-Sources Agensh, a Multi-Agent harness for coding","datePublished":"2026-10-25T03:32:59Z","url":"https://digestai.news/story/microsoft-open-sources-agensh-a-multi-agent-harness-for-coding"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}