Compare commits

...
@@ -2,9 +2,9 @@
title: "Readme"
task: ""
lineage_type: import
upstream_source: https://github.com/promptslab/awesome-prompt-engineering/blob/c6465ed6/README.md
upstream_sha: c6465ed6
imported_at: 2026-07-08
upstream_source: https://github.com/promptslab/awesome-prompt-engineering/blob/59ac64dd/README.md
upstream_sha: 59ac64dd
imported_at: 2026-07-17
prompt_class: catalogue
upstream_changes: accepted
author: upstream
@@ -856,7 +856,7 @@ These models established key concepts but are largely superseded for practical u
<!-- AUTORESEARCH-START -->
## πŸ”¬ Autonomous Research & Self-Improving Agents
> Auto-synced from [awesome-autoresearch](https://github.com/alvinunreal/awesome-autoresearch) Β· Last synced: 2026-07-08
> Auto-synced from [awesome-autoresearch](https://github.com/alvinunreal/awesome-autoresearch) Β· Last synced: 2026-07-17
### General-Purpose Descendants
@@ -911,6 +911,8 @@ These models established key concepts but are largely superseded for practical u
- [PouriaRouzrokh/LatteReview](https://github.com/PouriaRouzrokh/LatteReview) β€” Low-code Python package for **automated systematic literature reviews** via AI-powered agents.
- [LitLLM/LitLLM](https://github.com/LitLLM/LitLLM) β€” AI-powered literature review assistant using RAG for accurate, well-structured related-work sections in academic writing.
- [Agent Laboratory](https://agentlaboratory.github.io/) β€” Three-phase research pipeline: Literature Review β†’ Experimentation β†’ Report Writing, with specialized agents for each phase.
- [happyhappy-jun/writing-driven-autoresearch](https://github.com/happyhappy-jun/writing-driven-autoresearch) β€” Autoresearch-style harness that keeps a submittable paper from the first minute and drives every experiment from the claims in that draft, looping modify β†’ measure β†’ verify β†’ revise. 1st place at the [Ralphthon@ICML 2026](https://luma.com/hjuo7auc) autonomous-research hackathon.
- [AutoResearch-Factory/Agon](https://github.com/AutoResearch-Factory/Agon) β€” End-to-end research orchestrator built on one cornerstone principle, Prompt Economy (reusable loops, not one-off prompts), plus five supporting rules; runs scientist/coder/auditor loops across 10+ disciplines, same reusable-loop lineage as autoresearch but scaled to full research programs.
### Platform Ports & Hardware Forks