microsoft / microsoft/agent-framework
Possible complementary direction: LongHorizon-Harness for sustained agent tasks
@sphenry is already working on this.
Since Aug 12, 2026.
- Dominant language
- Python
- Stars
- 13.6k
- Forks
- 2.3k
- Avg merge
- 2d 45m
- Merged PRs (30d)
- 358
Description
Hi, I'd like to suggest a complementary direction for `agent-framework`.
Project:
https://github.com/AMAP-ML/LongHorizon-Harness
Your project focuses on an agent harness and orchestration layer.
LongHorizon-Harness focuses on carrying one task across many rounds without state drift. It keeps the goal and verified progress in durable state, starts each execution round with a fresh context, and uses an independent Auditor before accepting progress.
Why this may be useful here:
- A short workflow note could show how to avoid context drift and premature completion in a task that spans many rounds.
- it adds an outer task-lifecycle layer without claiming to replace the project's existing agent or runtime
If this direction fits, I can prepare a small documentation or example contribution following the repository's conventions.
I am part of the team behind LongHorizon-Harness, so I wanted to disclose that connection.
Paper:
https://arxiv.org/abs/2608.01964
Project page:
https://lh-harness.pages.dev
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.