Chain Of Thought Python Packages

kiln-ai

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

optillm

Optimizing inference proxy for LLMs

kiln-server

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

longguard

In-flight circuit breaker & loop recovery for LangGraph, LangChain, OpenAI & Anthropic agents. Catches reasoning loops, prevents runaway LLM costs with budget hard caps, and auto-injects Reflect & Pivot prompts.

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

cogitator

A Python toolkit for chain-of-thought prompting 🐍

openkreflux

OpenKreflux: Resilient multi-provider inference and chain-of-thought verification engine

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.

cot-redteam-agent

Red-team visible LLM reasoning — refusal quotes aren't success. Adaptive TUI, CI scan, OWASP tags, mock provider, proof-of-action agent lane.

the-compiler

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

tracedistill

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

cotarag

Agentic-AI framework w/o the headaches

thinkrouter

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

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

prompt-playoff

Prompt optimization and benchmarking for local LLMs: picks the right prompt technique for your task and measures it on Ollama. DSPy-compatible.

fragaria

Fragaria is a powerful and flexible Chain of Thought (CoT) reasoning API that leverages various Language Model (LLM) providers and incorporates Reinforcement Learning (RL) techniques to solve complex problems and answer intricate questions.

lsekit-sequentialthinking

Multi-step sequential thinking MCP server powered by large language models — structured reasoning with self-MoA and iterative thinking modes

kiln-studio

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