Awesome Autoresearch workflow
awesome-autoresearch
A collection of autonomous self-improvement loops and research agents that set hypotheses and test them themselves
- 2,565 ★ on the repository
- Last commit
Minimal access
Why this level
- Projects are often research ones and go stale fast
- Autonomous loops spend tokens unattended
Install
Manual install
Открыть README репозитория webfuse-com/awesome-autoresearch на GitHub
There is no installation: read the README and open the needed repositories.
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Projects are often research ones and go stale fast
- Autonomous loops spend tokens unattended
This is third-party code. Review the repository files before installing.
What it does
Awesome Autoresearch by Webfuse follows a narrow fast-changing field: agents that formulate hypotheses themselves, run experiments and improve their own results. Many projects in it are research ones and rest on the authors' enthusiasm. The CC0 license is stated in the README while GitHub shows NOASSERTION in the metadata.
Who it is for. For researchers and engineers who want to see how agent self-improvement loops are built today and to find code that can be run.
Good fit when
- You need to see which approaches to agent self-improvement exist
- You need projects where an agent runs experiments itself
- You need to follow fresh work in this field
Not a fit when
- You need a proven tool for work: projects are more often research ones
- You need an overview article: the collection has links with no analysis
Example request
Find three projects in the collection where an agent runs experiments itself and compare how each checks the result of its own workLimitations
Autonomous loops work unattended and burn tokens and many projects in this field are raw and go stale fast. Run them in an isolated environment with a spending limit and give them no access to working data.
How to disable. To stop it is enough to close the README. Projects launched from links are stopped and deleted together with their keys and cache.
FAQ
What is this collection about?
About agents that set hypotheses, run experiments and improve their own results.
Are the projects suitable for working tasks?
Many are research projects and change fast: for work take those under active development.
What license is it?
CC0 per the README, with GitHub showing NOASSERTION.
Discussion
No questions or reviews yet.
Related
WorkflowsAn autonomous research assistant: from idea and plan through experiments and analysis to a paper, relying only on real results
ARIS
ARIS (Auto-Research-In-Sleep)
A skill set for autonomous machine learning research: literature review, idea discovery, experiments and paper writing with review by a separate model
Autoresearch for skills
autoresearch
A skill that improves another skill: runs it on test inputs, scores outputs with binary checks and mutates the prompt
A multi-agent harness that verifies results by artifacts: stop hooks, an independent judge and an event log for Claude Code, Codex, Cursor and more
AI Research Skills
AI Research Skills Library
98 skills for ML research, from ideation and model training to inference, evaluation and paper writing
Awesome Agent Orchestrators
awesome-agent-orchestrators
A registry of orchestrators for coding agents: how they differ in launch, isolation and supported agents
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Awesome Autoresearch (this entry) | no | 2,565 | |
| Awesome Codex Subagents | no | 6,313 | role templates of subagents for Codex |
| Awesome Agent Orchestrators | no | 2,174 | a registry of orchestrators to compare launch and isolation |
README in short
The README describes a collection of autonomous self-improvement loops and research agents with links. The CC0 license is stated in the README.