Chain Of Thought Python Packages

optillm

Optimizing inference proxy for LLMs

kiln-ai

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

kiln-server

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

crystal-metrics

CRYSTAL: Beyond Final Answers: Benchmark for Transparent Multimodal Reasoning Evaluation | arXiv 2603.13099

reasonchain

A modular AI reasoning library for creating intelligent agents with advanced reasoning pipelines, memory management, and seamless LLM integration.

bulk-chain

A no-string API framework for deploying schema-based reasoning into third-party apps

cota

Build domain AI assistants with annotated dialogue examples - 通过标注对话示例，低成本构建可靠智能体

easyinstruct

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

pairadigm

Concept-Guided Chain-of-Thought (CGCoT) pairwise annotation tool for systematic text evaluation using LLMs. Generate breakdowns, compare items, compute scores, and validate against human judgments. Supports Ollama, Hugging Face, Google Gemini, OpenAI, and Anthropic models.

cogitator

A Python toolkit for chain-of-thought prompting 🐍

tracedistill

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract and a two-phase Train→Nudge schedule (silver-medal NVIDIA Nemotron reasoning recipe).

thinkrouter

Cut LLM reasoning-token costs by 60% with one line of code

the-compiler

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

cotarag

Cognitive Thought and Retrieval Augmented Generation - An advanced AI agent framework combining CoTAEngine and AcceleRAG

promptinject

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

brad-enrichment

Chain of Thought Gene Enrichment Report Generation

ultron-ai

⚡ ULTRON-AI: Advanced AI-powered code analysis with Chain of Thought and ReAct framework

fragaria

Advanced Chain of Thought (CoT) Reasoning API with Reinforcement Learning (RL)