Agent frameworks & infrastructure
Prompt engineering & prompt libraries
913 agents · most starred first
Prompt engineering & prompt libraries, page 9 of 10
Plugin to add a --json flag to the llm prompt command
A flexible system for managing and processing prompt templates
A comprehensive framework for systematic A/B testing, optimization, performance analytics, security, and monitoring of LLM prompts across multiple providers with enterprise-ready API
A lightweight Python library for optimizing and cleaning LLM inputs
A CLI tool for managing and comparing LLM prompts using semantic diffing
Git-style diff and version control for LLM prompts
Transform any LLM into a methodical thinker that excels at systematic reasoning like OpenAI o1 and DeepSeek R1
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steer vectors
An llm plugin to add structured JSON output support to LLMs
Constrain LLM generation to structured output, such as function calling and tool use
Universal tools for prompt engineering and LLM interactions.
A collection of preset efficient prompts packaged into LLM agents.
Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.
Load LLM templates from Fabric
Load LLM templates from local paths and cloud storage (S3, GCS, Azure) using any supported fsspec URL scheme.
Laod LLM templates from GitHub repositories
LLM template loader for Latitude - Load prompts from Latitude as LLM templates
Load LLM templates from SourceHut repositories
Remove characters from text while keeping it understandable for LLMs, saving on inference costs.
LLM fragment & template loaders for tmux scrollback and helpful prompt templates
从 YAML 配置生成标准化的 AI 协作规则文档 (llm.txt)
Type-safe LLM output parsing with Pydantic models and Jinja2 prompt templates
Utilities for cleaning and normalizing raw LLM output
git diff for LLM prompts
Format LLM language by using LALR(1) grammar. Supports JSON, XML, etc.
Git blame for prompts: incident archaeology, git-native prompt versioning, and a no-SaaS production runtime for LLM workflows
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Versioned prompts and Agent Skills with progressive context loading for production LLM apps
A comprehensive LLM Prompt Management System
Version, compare, and manage your LLM prompts. No API keys required. Bring your own model.
Prompt Perfection at Your Fingertips
A package for LLM tricks
MCTS + LLM + Prompt Engineering => Enhanced LLM Reponse Quality.
A prompt algebra for LLM orchestration. The code reads as its own specification.
No Prompt For LLM
Elegant Jinja2-based chat template parser for AI applications
A lightweight Python library to optimize functions using OpenAI's GPT model
Force LLMs to use a specific context-free grammar in completions
A passive agent for prompt engineering experiments with instruction-based context building
Prompt version control and A/B testing for LLM applications
A powerful toolkit for building, managing, and composing hierarchical prompts as code.
preLLM — One function for small LLM preprocessing before large LLM execution. Like litellm.completion() but with decomposition.
🙏🏼 Politely injects PLEASE into your LLM prompts. Because manners matter (kind of).
A zero-dependency CLI tool to prompt LLMs by reego.software
Library for managing and caching Google Docs prompts with templating support.
A simple, zero-dependency library to format prompts for various open-source LLMs.
A lightweight library for LLM prompt management, observability/tracing, and optimization
A library for optimizing PydanticAI agents prompts through iterative improvement and evaluation, built on top of PydanticAI + Pydantic Evals.
Controlled language model generation using regex
Get exact structure out of any language models with regular expressions.
Creating lightweight representations of objects for Large Language Model consumption
Clean, simplified schemas from Pydantic models for LLM prompts - less verbose than JSON Schema
A library of prompts for GenAI
LLM-powered ProServe manifest generator
Python SDK for the Sigil persona registry - inject personas into LLM system prompts
A wrapper of LLMs that biases its behaviour using prompts and contexts in a transparent manner to the end-users
A Python library to extract and correct JSON from LLM outputs
structured llm outputs
Universal Python library for Structured Outputs with any LLM provider
Guaranteed structured output from any LLM — with automatic retries and validation
Jinja2 Prompt Template for Swarmauri.
A lightweight, standalone library for managing hierarchical system prompts with support for global, primary, secondary, and numbered prompts
The official Python library for the system-prompt-storage API
Refine unstructured briefs into implementation-ready JSON via LLM7 and llmatch.
A library for optimizing LLM tasks, including prompt engineering and bandit-based training.
AI agent personalities for every tool. https://github.com/itallstartedwithaidea/agency-agents
LangChain Runnable client for TokenCrush prompt optimization API (/v1/crush)
Token-Oriented Object Notation – Optimised serialization JSON for LLMs
A lightweight markup language for structured text generation
Improve your AI prompts instantly for better results.
Claude Code Guidelines - Agentic System Prompts Repository
A dependency manager for agentic markdown — skills, agents, and prompts for your AI tools.
A web-based IDE for LangChain prompts
Rule Coherence Graph — detect conflicts in AI agent rule corpora.
Git-native prompt management for AI agent workflows
Jumping Rivers: Prompt Craft
Fully automatic censorship removal for language models
Generate DSPy Signatures from any prompt using a DSPy meta-program
Natural language to skillm DSL
Static, deterministic LLM prompt/payload compression that cuts input tokens 30-90% with zero extra model calls.
Practical, ready-to-use tools for LLM generated XML
A tiny, dependency-free tool belt for LLMs: token counting, cost estimation, retries, prompt templates, and text chunking.
Deterministic prompt builder on pydantic-stack-core (every prompt = a MetaStack of RenderablePieces) + cognition chains + optional grammar gate — the shared base of the chaincompiler ecosystem.
Bidirectional UUID<->numeric ID mapping to shrink LLM prompt token counts for large item lists.
Safe LLM prompt templating with validation guards
Encode JSON → TOON (40-60% token savings for LLMs!)
Universal declarative skills for agents
cohereny — runtime prompt adaptation for multi-LLM workflows (coming soon)
Provider-agnostic prompt optimization pipeline powered by LiteLLM.
Robustly extract, repair, and coerce structured data (JSON) from messy LLM text output.
Self-improving loop for your existing AI agent: write GOALS.md, agentopt measures the gap and closes it - prompts, params, tools, workflow. No model training. Under active development.
AI profiles shared across agentic harnesses
An agent that rewrites its own system prompt from execution feedback
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
Atlante command-line interface for structured, versionable AI agent prompts
Structured corpus of AGENTS.md — the written rules humans hand to AI agents | 人写给 AI 智能体的书面规约的结构化语料库
Encode data as token-efficient, LLM-friendly strings