CHATS-lab / verbalized-samplingLinks
Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.
☆611Updated last month
Alternatives and similar repositories for verbalized-sampling
Users that are interested in verbalized-sampling are comparing it to the libraries listed below
Sorting:
- Evolve your language agent with Agentic Context Engineering (ACE)☆439Updated last month
- An alignment auditing agent capable of quickly exploring alignment hypothesis☆759Updated 2 weeks ago
- ☆686Updated last week
- bloom - evaluate any behavior immediately 🌸🌱☆640Updated last week
- ☆235Updated last week
- Build common agent use-cases with deepagents library☆405Updated 3 weeks ago
- Multi-Agent Financial Research workflow☆152Updated 7 months ago
- Vibe-coding tools for the LlamaIndex ecosystem☆174Updated last month
- claude code system prompt☆697Updated 5 months ago
- Living memory for AI☆320Updated this week
- A comprehensive 0-to-1 guide for building self-improving LLM applications with DSPy framework☆195Updated 2 months ago
- Enterprise-grade memory framework for LLMs featuring GPU-optimized inference, vector storage, and automated scaling. Enables hyper-person…☆89Updated 7 months ago
- The lightweight framework for building agents☆167Updated last week
- An open source implementation of code execution with MCP (Programatic Tool Calling)☆612Updated 3 weeks ago
- A multi-agent LLM system for detecting and resolving cognitive dissonance.☆270Updated 2 months ago
- Context Engineering Course with DSPy☆206Updated 5 months ago
- An OpenSource Deep Research library with reasoning☆172Updated 3 weeks ago
- ☆221Updated 8 months ago
- An end-to-end Data Scientist☆458Updated 3 weeks ago
- MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents☆527Updated last week
- An agentic Machine Learning Engineer☆1,142Updated 3 weeks ago
- MCP-based Agent Deep Evaluation System☆142Updated 3 months ago
- Gemini-cli or claude code? Why not both? LangCode combines all CLI capabilities and models in one place ☂️!☆430Updated last month
- Terminal-based AI Coding Agent, similar to Claude Code, OpenAI Codex etc. but works with many more LLMs e.g. Gemini, Groq, Deepseek☆151Updated 7 months ago
- Aware - Deep Code Research Agent for Complex Codebase & Knowledge that “Act As Your Agentic Principal Engineer”☆392Updated 2 months ago
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆451Updated 4 months ago
- A curated list of awesome open-source libraries for context engineering (Long-term memory, MCP: Model Context Protocol, Prompt/RAG Compre…☆101Updated 5 months ago
- Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.☆578Updated 2 weeks ago
- ☆314Updated 3 weeks ago
- ☆787Updated last week