TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
-
Updated
Jul 25, 2025 - Python
#
prompt-optimization
Prompt engineering is the practice of designing and optimizing prompts to effectively guide large language models (LLMs) and generative AI systems. It improves AI responses by using clear instructions, relevant context, examples, and constraints to achieve accurate and reliable outputs.
Here are 268 public repositories matching this topic...
End-to-end Generative Optimization for AI Agents
python machine-learning ai optimization end-to-end optimizer agents autodiff large-language-models llm prompt-optimization agentic-agi agentic-workflow compound-systems generative-optimization
-
Updated
Jun 17, 2026 - Python
Build calibrated AI Functions from human feedback using Jev and GEPA.
-
Updated
Oct 3, 2026 - Python
A very fast, very minimal prompt optimizer
genetic-algorithm evolutionary-algorithm prompt-learning prompt-tuning prompt-engineering prompt-optimization
-
Updated
Jan 5, 2025 - Python
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
asynchronous parallel optimizer evolutionary-algorithms gradient-descent self-improvement agents ai-agents agent-framework skill-learning llm prompt-optimization llm-agents self-evolving-agents
-
Updated
Oct 10, 2026 - Python
A unified, modular framework for prompt optimization
prompt prompt-tuning llm prompt-engineering prompt-optimization automated-prompt-engineering automated-prompt-optimization
-
Updated
Sep 24, 2026 - Python
Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком уровне усилий её запускать. Каждый совет со ссылкой на официальную документацию. Без API-ключей, без зависимостей, офлайн.
python cli openai developer-tools codex astra zero-dependencies llm prompt-engineering anthropic prompt-optimization agent-skills claude-code gpt-6
-
Updated
Oct 5, 2026 - Python
Deterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.
-
Updated
Oct 2, 2026 - Python
Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically
-
Updated
Jun 23, 2026 - Python
Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other optimizable code.
python cli machine-learning optimization ai-agents gpu-kernels llm prompt-optimization agent-harness autoresearch
-
Updated
Oct 6, 2026 - Python
AI agent that turns your rough ideas into perfect image generation prompts. 7-component formula, 70+ creative techniques, 9 domain modes.
gemini text-to-image claude creative-ai ai-art ai-agent prompt-engineering ai-image-generation anthropic prompt-optimization google-gemini prompt-templates claude-code image-prompts nano-banana
-
Updated
Mar 25, 2026 - Python
Typed functions whose body a language model writes: run them on tables, measure how often they're right, make them better. Python, TypeScript, R and Julia.
-
Updated
Oct 10, 2026 - Python
SCOPE: Self-evolving Context Optimization via Prompt Evolution - A framework for automatic prompt optimization
-
Updated
Mar 26, 2026 - Python
Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).
agents llm prompt-optimization agent-skills pareto-optimization claude-code claude-skill meta-harness
-
Updated
Jun 14, 2026 - Python
Claude Code for DSPy: Comprehensive CLI to Optimize Your DSPy Code. our AI-Powered DSPy Development Assistant
-
Updated
Sep 14, 2026 - Python
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
python mcp ai-agents claude dspy llm prompt-engineering evals llm-evaluation prompt-optimization agentic-ai model-context-protocol agent-skills agent-optimization gepa
-
Updated
Oct 12, 2026 - Python
State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more
python nlp machine-learning natural-language-processing ai experimental artificial-intelligence openai few-shot-learning dspy large-language-models llm prompt-engineering prompt-optimization meta-prompting
-
Updated
Apr 11, 2026 - Python
RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).
-
Updated
Jun 12, 2026 - Python
A lightweight implementation of the GEPA (Genetic-Pareto) prompt optimization method for large language models.
open-source gemini google-summer-of-code gemma gemini-api prompt-tuning large-language-models student-vscode ollama prompt-optimization fortheloveofcode
-
Updated
Aug 12, 2025 - Python
MCP server integrating GEPA (Genetic-Evolutionary Prompt Architecture) for automatic prompt optimization with Claude Desktop
python ai mcp evolutionary-algorithms genetic-algorithms prompt-optimization gemini-ai claude-desktop
-
Updated
Nov 10, 2025 - Python
- Followers
- 771 followers
- Website
- github.com/topics/prompt-engineering
- Wikipedia
- Wikipedia